Biological nitrogen and phosphorus removal system for sewage

Abstract

The invention provides a biological nitrogen and phosphorus removal system for sewage, and relates to the technical field of sewage treatment. Comprising an online monitoring module, a carbon source demand calculation module, a carbon source distribution control module, a biological reaction regulation module and a self-learning optimization module which are connected in sequence. The on-line monitoring module collects operation parameters of each process section in real time; the carbon source demand calculation module dynamically calculates the carbon source demand proportion by analyzing the rate change of denitrification and phosphorus accumulation processes; the carbon source distribution control module automatically adjusts carbon source feeding according to a required proportion; the biological reaction adjusting module adjusts aeration and hydraulic parameters in a linkage mode, and metabolism complementation of denitrification and phosphorus removal is promoted; and the self-learning optimization module continuously optimizes a system operation strategy through deep learning. According to the invention, intelligent distribution of the carbon source between denitrifying bacteria and phosphorus-accumulating bacteria is realized, the problem of low nitrogen and phosphorus removal efficiency caused by carbon source competition is solved, and the sewage treatment efficiency and the operation stability are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage treatment, in particular to a sewage biological denitrification and phosphorus removal system. BACKGROUND

[0002] In the field of biological sewage treatment, it is a complex and challenging task to simultaneously achieve efficient denitrification and phosphorus removal. Currently, the addition of carbon source in this field is often roughly proportionally adjusted based on the inflow or the single concentration of a specific pollutant; key operating parameters such as aeration and hydraulic retention time are also set empirically or adjusted slightly within a certain range. This control method regards the denitrification process and the phosphorus removal process as two relatively independent or even competing processes, lacking the ability to finely perceive and cooperatively control the dynamic competition relationship between the two processes in terms of carbon source utilization. However, due to the inability to identify the instantaneous proportional change in carbon source demand of denitrifying bacteria and phosphorus accumulating bacteria in real time, the system has difficulty in making optimal allocation decisions under limited carbon source conditions, often leading to a decline in metabolic efficiency of one group of bacteria due to insufficient carbon source, while the other group may excessively consume carbon source, resulting in resource waste and fluctuations in effluent water quality. SUMMARY

[0003] To achieve the above object, the present application is implemented by the following technical scheme: a sewage biological denitrification and phosphorus removal system, comprising: An online monitoring module is used to obtain real-time operating data of the influent, the anaerobic zone, the anoxic zone and the effluent end during the biological reaction of sewage, the operating data including dissolved oxygen concentration, oxidation-reduction potential, nitrate nitrogen, nitrite nitrogen, total phosphorus and volatile fatty acid concentration; and the collected data are input to a carbon source demand calculation module in time sequence; The carbon source demand calculation module constructs a dynamic discrimination logic of carbon source competition relationship based on multi-dimensional data, calculates the instantaneous carbon source demand proportion of denitrifying bacteria and phosphorus accumulating bacteria by analyzing the change trend of nitrate reduction rate in the denitrification process and the relative change of phosphorus release rate and phosphorus uptake rate in the phosphorus removal process, and accordingly preferentially allocates carbon source to the anoxic zone or the anaerobic zone, or maintains the original proportion when balanced; A carbon source allocation control module is connected with a carbon source injection device and a mixed aeration unit, used to automatically adjust the carbon source injection point and injection rate according to the allocation signal output by the carbon source demand calculation module, to realize dynamic carbon source supply in different reaction zones; under the condition of insufficient carbon source, the organic carbon uptake of phosphorus accumulating bacteria in the anaerobic stage is preferentially guaranteed to maintain the energy metabolism activity of phosphorus accumulating bacteria, and a small amount of carbon source is supplemented to maintain the reduction efficiency of nitrate in the denitrification stage; A biological reaction regulation module is linked with an aeration system and a hydraulic regulation device, adjusts the dissolved oxygen set value, the aeration time proportion and the hydraulic retention time based on the real-time carbon source allocation state, so that the denitrification process and the phosphorus removal process form a complementary relationship in metabolic rhythm; The self-learning optimization module collects and analyzes data of the entire operation cycle, establishes a parameter-performance correlation system through a deep learning model, identifies the carbon source allocation characteristics under different influent water quality conditions, and corrects the decision threshold in the carbon source demand calculation module, so that it gradually forms the regulation ability for different influent conditions.

[0004] The online monitoring module is used to obtain the operation data of the influent, the anaerobic zone, the anoxic zone and the effluent end in real time during the biological reaction of wastewater, and the operation data includes but is not limited to dissolved oxygen concentration, oxidation-reduction potential, nitrate nitrogen, nitrite nitrogen, total phosphorus and volatile fatty acid concentration. The online monitoring module collects high-frequency data through a multi-parameter water quality sensor array deployed in the corresponding reaction zone. The sampling frequency can be dynamically adjusted according to the influent load, ranging from 1 to 5 minutes each time. The collected data are time-stamped in chronological order and input into the carbon source demand calculation module to ensure the time sequence consistency of the data stream and provide a reliable data basis for subsequent dynamic analysis.

[0005] The carbon source demand calculation module constructs a dynamic discrimination logic of carbon source competition relationship based on multi-dimensional data, establishes a carbon source demand evaluation model based on microbial metabolic kinetics by analyzing the change trend of nitrate reduction rate in the denitrification process and the relative change of phosphorus release rate and phosphorus uptake rate in the phosphorus accumulation process. Specifically, the nitrate reduction rate is obtained by real-time calculation of the reduction amount of nitrate concentration per unit time, and the phosphorus release rate and phosphorus uptake rate are obtained by monitoring the rising rate of phosphorus concentration in the anaerobic zone and the falling rate of phosphorus concentration in the aerobic zone, respectively. By comparing the instantaneous change gradient of the two rates, the instantaneous carbon source demand ratio of denitrifying bacteria and phosphorus accumulating bacteria is calculated. The calculation of this ratio not only considers the rate value at the current moment, but also introduces the change trend in the past period of time for weighted correction to avoid misjudgment caused by instantaneous fluctuation. According to this, carbon source allocation instructions are generated to allocate carbon source preferentially to the anoxic zone or the anaerobic zone, or maintain the original allocation ratio when the demand of the two zones is balanced.

[0006] The carbon source allocation control module is connected with the carbon source injection device and the mixed aeration unit through an industrial field bus, and is used to automatically adjust the selection of carbon source injection point and the injection rate according to the allocation signal output by the carbon source demand calculation module, that is, to inject at the first end of the anaerobic zone, the first end of the anoxic zone or multiple points at the same time to realize dynamic carbon source supply in different reaction zones. The module has a priority control strategy built-in. Under the condition that the system judges that the total amount of carbon source is insufficient, the priority is given to the organic carbon absorption of phosphorus accumulating bacteria in the anaerobic stage to maintain the energy storage metabolic activity of phosphorus accumulating bacteria and prevent irreversible decline of phosphorus removal efficiency caused by loss of activity. At the same time, a trace carbon source compensation program is started in the denitrification stage to inject the minimum necessary amount of carbon source into the anoxic zone to maintain the basic reduction efficiency of nitrate and avoid the accumulation of nitrate nitrogen.

[0007] The biological reaction regulation module is linked with the aeration system and the hydraulic regulation device through a control loop, and based on the real-time carbon source distribution state, adjusts the dissolved oxygen set value, the aeration time ratio and the hydraulic retention time; the core control target of the module is to make the denitrification process and the phosphorus removal process complementary in metabolic rhythm through parameter adjustment; for example, when the carbon source is preferentially distributed to the anaerobic zone, the module correspondingly reduces the dissolved oxygen set value of the subsequent aerobic zone and appropriately prolongs the hydraulic retention time of the anaerobic stage, to create more favorable conditions for sufficient phosphorus release and carbon absorption of phosphorus accumulating organisms; and when the carbon source is inclined to the anoxic zone, the lower limit of the dissolved oxygen set value is increased and the aeration timing is optimized to ensure sufficient nitrification process and provide sufficient substrate for denitrification.

[0008] The self-learning optimization module collects and stores data of the entire operation cycle, and establishes a nonlinear correlation system between system operation parameters and denitrification and phosphorus removal performance indicators through a deep learning model; the deep learning model adopts a long short-term memory network structure to identify carbon source distribution characteristic patterns under different influent water quality conditions, such as low carbon-nitrogen ratio and high phosphorus load; through periodic model training and verification, the correction parameters of the decision threshold value in the carbon source demand calculation module are output, so that the self-adaptive regulation and control ability to influent water quality fluctuations is gradually formed, and the evolution from rule-based control to data-driven intelligent control is realized.

[0009] As a further technical solution, the carbon source demand calculation module is provided with a dynamic threshold updating unit, which, when the denitrification stage and the phosphorus accumulation stage change alternately, mines the time shift law of the correlation between the dissolved oxygen, the oxidation-reduction potential and the nitrate reduction rate in the historical operation database through correlation analysis; based on the law, the trigger threshold of carbon source preferential distribution is adjusted by a small amplitude, and the adjustment amplitude does not exceed ±15% of the original threshold; the dynamic threshold updating process compares the carbon source utilization rate change trend of the current operation cycle with that of the previous cycle, calculates the difference range between the carbon source utilization saturation point of denitrifying bacteria and the carbon storage stability point of phosphorus accumulating organisms through a sliding window algorithm, and takes the stable interval of the difference value in continuous multiple cycles as a new decision interval, so that the carbon source distribution strategy is freed from the dependence on fixed proportion parameters, and flexible control based on the actual operation state of the system is realized.

[0010] As a further technical solution, the online monitoring module includes a set of time-synchronized sampling logic, which coordinates the sampling devices at the water inlet end and the water outlet end through a unified clock signal to achieve synchronized collection of key water quality indicators within the same hydraulic retention period; by normalizing the dissolved oxygen, total phosphorus and volatile fatty acid concentration data within the same period, the analysis deviation caused by different dimensions and orders of magnitude is eliminated, and a carbon source utilization efficiency sequence reflecting the conversion efficiency of carbon sources in the system is generated; the carbon source demand calculation module identifies the timing characteristics of carbon source consumption in different reaction zones according to the sequence, and when the peak detection algorithm identifies that the carbon source consumption peak is ahead of or lags behind the expected time point by more than one sampling period, the data sampling time step is automatically adjusted, the response rate of the subsequent carbon source prediction model is corrected by shortening or lengthening the sampling interval, and the control system can timely track the changes in the microbial metabolic state.

[0011] As a further technical solution, the carbon source distribution control module is provided with feedback adjustment logic, which monitors the oxidation-reduction potential fluctuation amplitude of the anoxic zone and the anaerobic zone in real time after the carbon source injection rate changes; a dynamic oxidation-reduction potential stable interval based on historical stable operation data is set, and when the oxidation-reduction potential change amplitude of any zone exceeds the set interval for three consecutive sampling periods, a trace compensation program is triggered; before the carbon source supply reaches stability again, the output intensity of the aeration system is temporarily limited and the design hydraulic retention time of the anoxic zone is extended by 10%-20%, so that the denitrifying bacteria and phosphorus accumulating bacteria community have enough time to re-establish metabolic balance under the new carbon source distribution ratio; the real-time fluctuation of the microbial metabolic state is indirectly reflected through the slight change of the oxidation-reduction potential, and the synchronous convergence of carbon source dosing operation and biological biochemical reaction is realized.

[0012] As a further technical solution, the biological reaction adjustment module also includes a phased aeration adjustment unit, which is activated when the carbon source demand calculation module determines that the carbon source demand of phosphorus accumulating bacteria is dominant; after activation, the dissolved oxygen set value of the aerobic zone is reduced by 0.5-1.0 mg / L, and the actual hydraulic retention time of the anaerobic stage is temporarily extended by 15%-30% through control of the water inlet valve or internal reflux valve; the aeration adjustment unit determines the carbon source consumption trend according to the carbon source consumption change rate curve output by the carbon source demand calculation module, and slows down the aeration intensity in advance before the predicted carbon absorption peak of phosphorus accumulating bacteria is reached, to realize smooth metabolic transition from anaerobic environment to anoxic environment; this control strategy enables the phosphorus accumulating bacteria to complete most of the energy storage when the carbon source distribution peak is reached, and the denitrifying bacteria can fully utilize the intermediate products released by the phosphorus accumulating bacteria, such as low molecular weight fatty acids, for denitrification in the anoxic stage, thereby forming a dynamically complementary biological metabolic rhythm in terms of timing.

[0013] As a further technical solution, the self-learning optimization module utilizes the difference characteristics between multi-cycle data to establish an operation mode recognition logic when modeling the deep learning model for the operation cycle data; this logic classifies different water quality modes such as high-nitrogen low-carbon mode, nitrogen-phosphorus balanced mode, etc. by analyzing the change trend of the ratio of total nitrogen to total phosphorus in the influent, and selects the most suitable carbon source allocation strategy verified in historical data for each mode as the initial control parameter; when the online monitoring module detects that the change rate of key water quality parameters such as influent COD and ammonia nitrogen exceeds the preset range, the system temporarily switches from the normal optimization mode to the high-response mode, in which the data update frequency is doubled and the decision adjustment period of the carbon source allocation control module is correspondingly shortened, thereby quickly adapting to the mutation of the influent water quality and preventing the system performance from deteriorating sharply.

[0014] As a further technical solution, the deep learning model of the self-learning optimization module adopts a phased target updating logic in the parameter training process, which divides the training process into three progressive stages: in the early training stage, the carbon source utilization rate of the system is taken as the main optimization target to quickly establish the basic mapping relationship between carbon source addition and consumption; in the middle training stage, the difference between the denitrification rate and the phosphorus absorption rate is minimized as the optimization criterion to guide the model to learn how to balance the carbon source demand of the two competing processes; in the later training stage, the comprehensive ratio of the system unit energy consumption to the nitrogen and phosphorus removal rate is taken as the final optimization target to promote the model to realize the leap from local optimization to global energy efficiency optimization; this phased target updating logic enables the self-learning process to be gradual and progressive, gradually transitioning from basic carbon source efficiency control to complex whole-process comprehensive optimization.

[0015] As a further technical solution, a bidirectional data verification process is provided between the carbon source demand calculation module and the self-learning optimization module for periodic correction of prediction bias; this process is automatically executed at the end of each complete operation cycle, and the system performs difference analysis on the actual operation record of the carbon source allocation control module and the corresponding effluent denitrification and phosphorus removal results such as total nitrogen and total phosphorus removal rate; when the difference exceeds the dynamic threshold set based on historical performance data, the self-learning optimization module starts the correction program, generates a new set of prediction correction parameters and feeds them back to the decision core of the carbon source demand calculation module, replacing the poorly performing parameter set, thereby forming a closed-loop optimization system from decision-making to execution to verification and correction, ensuring the continuous improvement and long-term stability of the system performance.

[0016] The present application provides a sewage biological denitrification and phosphorus removal system, which has the following beneficial effects: 1、The present application solves the problem of rigid carbon source allocation caused by the inability to real-time perceive the competition situation between denitrifying bacteria and phosphorus accumulating bacteria by constructing a dynamic carbon source demand judgment logic based on multi-dimensional real-time data and calculating the instantaneous carbon source demand ratio, thereby improving the precision and utilization efficiency of carbon source addition.

[0017] 2、The present application solves the difficult problem that the two biological processes of denitrification and phosphorus removal are difficult to coordinate in metabolic rhythm by dynamically adjusting the carbon source distribution according to the instantaneous carbon source demand ratio, and adjusting the biological reaction parameters such as dissolved oxygen and hydraulic retention time in linkage, improves the metabolic complementarity between different reaction units inside, makes the energy reserve of polyphosphorus bacteria and the nitrate reduction process of denitrifying bacteria form dynamic coupling, thereby improving the overall stability of nitrogen and phosphorus removal while reducing the fluctuation risk caused by endogenous competition.

[0018] 3、The present application solves the core bottleneck of insufficient self-adaptive ability in the face of complex and variable influent conditions by using a self-learning optimization module and a deep learning model to establish a parameter and performance correlation system to continuously correct the decision threshold, and improves the ability of the system to learn and optimize its core control strategy from dynamic operation data. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described below in a clear and complete manner. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments; based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0020] The online monitoring module obtains real-time operation data through sensors arranged at the influent end, the anaerobic zone, the anoxic zone and the effluent end, including dissolved oxygen concentration, oxidation-reduction potential, nitrate nitrogen concentration, nitrite nitrogen concentration, total phosphorus concentration and volatile fatty acid concentration; the measurement accuracy of the dissolved oxygen sensor is ±0.1 mg / L, the oxidation-reduction potential measurement range covers -1000 mV to 1000 mV, and the detection limit of the nitrate nitrogen analyzer is 0.1 mg / L; all sensors maintain time synchronization through a unified clock signal, and the data acquisition frequency is set to once every 3 minutes; after the collected data is filtered, it is transmitted to the carbon source demand calculation module in chronological order.

[0021] The carbon source demand calculation module constructs a dynamic discrimination logic of carbon source competition relationship based on the received multi-dimensional data; the carbon source demand calculation module calculates the instantaneous carbon source demand proportion of denitrifying bacteria and phosphorus accumulating bacteria by analyzing the change trend of nitrate reduction rate in the denitrification process and the relative change of phosphorus release rate and phosphorus uptake rate in the phosphorus accumulation process; the calculation of the nitrate reduction rate uses the monitoring data in the last 30 minutes to obtain the change slope through linear regression algorithm; the calculation of the phosphorus release rate is obtained by monitoring the rising rate of phosphorus concentration in the anaerobic zone; when the nitrate reduction rate continuously increases while the phosphorus release rate remains stable, it is determined that the carbon source demand of denitrifying bacteria is dominant; when the phosphorus release rate rapidly rises while the nitrate reduction rate changes little, it is determined that the carbon source demand of phosphorus accumulating bacteria is dominant; the system sets the carbon source demand proportion threshold values as 1.15 and 0.85; when the proportion value calculated in three consecutive monitoring periods is greater than 1.15, an instruction is generated to allocate carbon source preferentially to the anoxic zone; when the proportion value is less than 0.85, an instruction is generated to allocate carbon source preferentially to the anaerobic zone; when the proportion value is between 0.85 and 1.15, the original allocation proportion is maintained.

[0022] The carbon source distribution control module automatically adjusts the carbon source injection point and injection rate according to the distribution signal output by the carbon source demand calculation module; the carbon source distribution control module is directly connected with the carbon source injection device and independently controls the carbon source addition in the anaerobic zone and the anoxic zone; in the implementation process, when it is necessary to increase the carbon source addition in the anoxic zone, the addition rate of the corresponding injection point is increased by 30% from the reference value, while the addition rate in the anaerobic zone is reduced by 30%; under the condition of insufficient carbon source, the system preferentially guarantees the carbon source supply in the anaerobic zone, ensuring that the allocation proportion is not less than 60% of the total carbon source amount; at the same time, the minimum necessary amount of carbon source addition is maintained in the denitrification stage, and the basic efficiency of nitrate reduction reaction is ensured through the trace carbon source compensation mechanism; the adjustment of the carbon source addition rate adopts a gradual adjustment mode, and a system stabilization time is reserved after each adjustment, and the control effect is verified by monitoring the change of redox potential.

[0023] The biological reaction adjustment module adjusts the operating parameters of the system based on the real-time carbon source distribution state; the module is linked with the aeration system and the hydraulic regulation device, and adjusts the dissolved oxygen set value, the aeration time proportion and the hydraulic retention time according to the allocation proportion of carbon source in different reaction zones; when the carbon source is mainly allocated to the anaerobic zone, the biological reaction adjustment module reduces the dissolved oxygen set value in the aerobic zone from 2.0 mg / L to 1.3 mg / L, and prolongs the hydraulic retention time in the anaerobic zone from 1.5 hours to 1.7 hours by adjusting the inlet valve; when the carbon source is mainly allocated to the anoxic zone, the dissolved oxygen set value in the aerobic zone is increased to 2.3 mg / L, and the internal reflux ratio of the mixed liquid is also increased; these adjustments make the denitrification process and the phosphorus removal process complementary in metabolic rhythm, and improve the overall treatment efficiency of the system.

[0024] The self-learning optimization module collects and analyzes data of the entire operation cycle, and establishes a parameter-performance correlation system through a deep learning model. The self-learning optimization module uses a time series prediction model to analyze historical operation data and identify carbon source allocation characteristics under different influent water quality conditions. During the training process of the deep learning model, the system takes the balance of carbon source utilization rate, denitrification rate, and phosphorus absorption rate, and the comprehensive energy efficiency of the system as the stage optimization target. When the influent water quality changes, the self-learning optimization module automatically selects the most suitable carbon source allocation strategy by analyzing the trend of the ratio of total nitrogen to total phosphorus in the influent, wherein the carbon source allocation strategy is a strategy solution based on existing experience and historical cases. When the rate of change of water quality parameters exceeds the normal range, the system switches to a high response mode, increases the data update frequency, and shortens the carbon source adjustment period.

[0025] The online monitoring module includes time-synchronized sampling logic to ensure that key water quality indicators are collected at the influent end and the effluent end within the same hydraulic retention period. The dissolved oxygen, total phosphorus, and volatile fatty acid concentrations collected are normalized to generate a carbon source utilization efficiency sequence. When the time of the carbon source consumption peak is detected to deviate significantly from the expected value, the system automatically adjusts the data sampling time step from every 3 minutes to every 2 minutes to correct the response rate of subsequent carbon source prediction.

[0026] The dynamic threshold updating unit in the carbon source demand calculation module makes a slight adjustment to the carbon source priority allocation threshold based on historical operation data when the denitrification stage and the phosphorus accumulation stage alternate. The adjustment process calculates the difference range between the carbon source utilization saturation point of denitrifying bacteria and the carbon storage stability point of phosphorus accumulating bacteria by comparing the carbon source utilization rate trend of the current cycle with that of the previous cycle, and uses the difference stability zone as the new decision interval. For example, when it is detected that the carbon source utilization efficiency of denitrifying bacteria is continuously improving, the carbon source demand proportion threshold is increased accordingly, so that the system tends to allocate more carbon sources to the anoxic zone.

[0027] The feedback adjustment logic is provided in the carbon source allocation control module to monitor the redox potential fluctuation amplitude of the anoxic zone and the anaerobic zone in real time after the carbon source injection rate changes. When the redox potential change amplitude exceeds the set stability interval, a trace compensation program is triggered to temporarily limit the aeration intensity and prolong the reaction time in the anoxic zone. The stability interval of the redox potential is determined based on the statistical characteristics of the historical data at this point, and the range of 25% to 75% of the historical data is taken.

[0028] The phase aeration adjustment unit in the biological reaction regulation module automatically reduces the dissolved oxygen set value and temporarily prolongs the anaerobic stage residence time when it is judged that the carbon source demand of phosphorus accumulating bacteria is dominant; the carbon source consumption trend is judged according to the change rate output by the carbon source demand calculation module, and the metabolic transition between the anaerobic zone and the anoxic zone is realized by slowing down aeration in advance before the carbon absorption peak of phosphorus accumulating bacteria; when the detection of volatile fatty acid concentration begins to decline, the aeration adjustment program is started, and the dissolved oxygen concentration in the aerobic zone is gradually reduced.

[0029] The deep learning model of the self-learning optimization module adopts a phased target updating logic in the parameter training process; in the early training stage, the carbon source utilization rate is the main optimization target, in the middle stage, the difference between the denitrification rate and the phosphorus absorption rate is minimized as the optimization criterion, and in the later stage, the comprehensive ratio of system energy consumption and nitrogen and phosphorus removal rate is taken as the final target; the duration of each training stage is dynamically adjusted according to the model convergence, and usually the early training lasts for one hundred cycles, the middle training lasts for fifty cycles, and the later training lasts for twenty cycles.

[0030] A bidirectional data verification process is provided between the carbon source demand calculation module and the self-learning optimization module, at the end of each running cycle, the system carries out difference analysis on the carbon source allocation record and the corresponding denitrification and phosphorus removal results; when the difference exceeds the set threshold, the self-learning optimization module generates new prediction correction parameters and feeds back to the carbon source demand calculation module; the difference threshold is usually set to 15%, when the deviation between the predicted value and the measured value of total nitrogen or total phosphorus exceeds the threshold for three consecutive cycles, the parameter correction program is triggered.

[0031] The cooperative operation between the modules of the present application ensures that the system can maintain excellent treatment performance under different influent conditions, and at the same time, through the self-learning function, the operation strategy is continuously optimized, realizing efficient and stable biological denitrification and phosphorus removal effect.

[0032] Although embodiments of the present application 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 therein without departing from the principles and spirit of the application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A biological nitrogen and phosphorus removal system for wastewater, characterized in that, include: The online monitoring module is used to acquire real-time operational data from the influent, anaerobic zone, anoxic zone, and effluent during the wastewater biological reaction process. The operational data includes dissolved oxygen concentration, oxidation-reduction potential, nitrate nitrogen, nitrite nitrogen, total phosphorus, and volatile fatty acid concentration. The collected data are input into the carbon source demand calculation module in chronological order. The carbon source demand calculation module constructs a dynamic discrimination logic for carbon source competition based on multidimensional data. By analyzing the changing trend of nitrate reduction rate in the denitrification process and the relative changes of phosphorus release rate and phosphorus uptake rate in the polyphosphate accumulation process, it calculates the instantaneous carbon source demand ratio of denitrifying bacteria and polyphosphate accumulation bacteria. Based on this, carbon sources are preferentially allocated to anoxic or anaerobic areas, or the original ratio is maintained at equilibrium. The carbon source distribution control module is connected to the carbon source injection device and the mixing aeration unit. It is used to calculate the distribution signal output by the module according to the carbon source demand, and automatically adjust the carbon source injection point and injection rate to realize dynamic carbon source supply in different reaction zones. Under the condition of insufficient carbon source, priority is given to ensuring the organic carbon absorption of polyphosphate bacteria in the anaerobic stage to maintain the energy storage and metabolic activity of polyphosphate bacteria. In the denitrification stage, the reduction efficiency of nitrate is maintained by compensating with trace carbon sources. The biological reaction regulation module is linked with the aeration system and hydraulic regulation device. Based on the real-time carbon source distribution status, it adjusts the dissolved oxygen setpoint, aeration time ratio and hydraulic retention time, so that the denitrification process and the phosphorus removal process form a complementary relationship in metabolic rhythm. The self-learning optimization module collects and analyzes data throughout the entire operation cycle, establishes a parameter-performance correlation system through a deep learning model, identifies the carbon source allocation characteristics under different influent water quality conditions, and corrects the decision threshold in the carbon source demand calculation module, so that it gradually forms the ability to regulate different influent conditions.

2. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that: The carbon source demand calculation module includes a dynamic threshold update unit. This unit adjusts the carbon source priority allocation threshold slightly based on the time offset between dissolved oxygen, redox potential, and nitrate reduction rate in historical operating data as the denitrification and polyphosphate accumulation stages alternate. This allows the system to automatically correct the carbon source supply strategy under conditions of significant water quality fluctuations. The dynamic threshold update process calculates the difference between the carbon source utilization saturation point of denitrifying bacteria and the carbon storage stability point of polyphosphate accumulation bacteria by comparing the current cycle with the previous cycle. The stable difference zone is used as the new decision interval, so that carbon source allocation no longer depends on a fixed ratio.

3. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that: The online monitoring module includes a set of time-synchronized sampling logic, which is used to collect key water quality indicators at both the inlet and outlet ends. By normalizing the concentrations of dissolved oxygen, total phosphorus, and volatile fatty acids within the same period, a carbon source utilization efficiency sequence is generated. The carbon source demand calculation module identifies the temporal characteristics of carbon source consumption in different reaction zones based on the carbon source utilization efficiency sequence. When the peak carbon source consumption is detected to be earlier or later, the response rate of subsequent carbon source prediction is corrected by adjusting the data sampling time step.

4. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that: The carbon source allocation control module is equipped with feedback regulation logic to monitor the fluctuation range of redox potential in the anoxic and anaerobic zones in real time after changes in the carbon source injection rate. When the detected redox potential fluctuation exceeds the set stable range, a micro-compensation program is triggered to temporarily limit the aeration intensity and extend the reaction time in the anoxic zone before the carbon source supply stabilizes, allowing the microbial community to re-establish metabolic balance under the new carbon source allocation ratio. The micro-changes in redox potential reflect the real-time fluctuations in the metabolic state of microorganisms, achieving synchronous convergence of carbon source allocation and biological reaction.

5. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that: The biological reaction regulation module also includes a phased aeration adjustment unit, which automatically reduces the dissolved oxygen setpoint and briefly extends the anaerobic stage residence time when it is determined that the carbon source demand of polyphosphate-accumulating bacteria is dominant. The aeration adjustment unit judges the carbon source consumption trend based on the rate of change output by the carbon source demand calculation module. By slowing down aeration before the peak carbon absorption of polyphosphate-accumulating bacteria, a metabolic transition between the anaerobic and anoxic zones is achieved, allowing polyphosphate-accumulating bacteria to complete energy storage before the peak carbon source distribution is reached. Subsequently, denitrifying bacteria can make full use of the intermediate products they release during the anoxic stage to carry out denitrification reactions, forming a dynamic and complementary biological metabolic rhythm.

6. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that: When the self-learning optimization module models the data from the operating cycle using deep learning, it establishes an operating mode recognition logic by utilizing the differences in data from multiple cycles. By identifying the changing trend of the total nitrogen to total phosphorus ratio in the influent, it selects the most suitable carbon source allocation strategy and updates the calculation parameters of the carbon source demand calculation module in real time. When the rate of change of water quality parameters is detected to exceed the preset range, it temporarily switches to a high-response mode, increases the data update frequency, and shortens the carbon source adjustment cycle to quickly adapt to sudden changes in influent water quality.

7. A wastewater biological nitrogen and phosphorus removal system according to claim 6, characterized in that: The deep learning model in the self-learning optimization module adopts a phased target update logic during parameter training. In the early stage of deep learning model training, the main optimization target is carbon source utilization rate. In the middle stage, the optimization criterion is to minimize the difference between denitrification rate and phosphorus absorption rate. In the later stage, the comprehensive ratio of system energy consumption and nitrogen and phosphorus removal rate is used as the final target. This phased target update logic enables it to gradually transition from carbon source efficiency control to overall process optimization.

8. The wastewater biological nitrogen and phosphorus removal system according to claim 1, characterized in that, A two-way data verification process is set up between the carbon source demand calculation module and the self-learning optimization module to periodically correct prediction biases. At the end of each operating cycle, the system performs a difference analysis between the carbon source allocation record and the corresponding nitrogen and phosphorus removal results. When the difference exceeds the set threshold, the self-learning optimization module regenerates new prediction correction parameters and feeds them back to the carbon source demand calculation module.