Energy-saving-oriented intelligent decision method for operation mode of key equipment in sewage treatment

Abstract

This invention relates to the field of wastewater treatment technology and discloses an intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction. The method includes: acquiring multi-dimensional process sensing data from the biological treatment tank; calculating the actual oxygen demand rate based on a microbial metabolic activity state extrapolation model; constructing an energy efficiency characteristic model of the aeration system; generating a target oxygen supply rate command; and jointly optimizing and solving the setpoints of blower speed and regulating valve opening, and then issuing the command for execution. The system includes units for multi-source data acquisition, oxygen demand rate extrapolation, energy efficiency modeling, oxygen supply demand analysis, joint optimization decision-making, and command issuance. This invention achieves a 12% to 18% reduction in electricity consumption per ton of water by precisely matching microbial metabolic needs with aeration oxygen supply and embedding optimal energy efficiency control, significantly improving energy efficiency and effluent stability.

Description

Technical Field

[0001] This invention belongs to the field of wastewater treatment technology, specifically relating to an intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction. Background Technology

[0002] With accelerating urbanization and increasingly stringent environmental standards, wastewater treatment systems are evolving towards intelligence and precision. As a core component of wastewater treatment, biological treatment processes rely on the coordinated operation of key equipment (such as blowers, agitators, and return pumps) to maintain the metabolic activity of the microbial community. The aeration system plays a crucial role in providing dissolved oxygen to the reaction tank, typically accounting for over 50% of the plant's total electricity consumption. Traditional operating modes often employ fixed-sequence control or simple feedback mechanisms based on preset dissolved oxygen thresholds, lacking the ability to perceive and respond in real-time to complex disturbances such as fluctuations in influent water quality, microbial metabolic dynamics, and changes in ambient temperature. This makes it difficult to balance treatment efficiency and energy efficiency in actual system operation.

[0003] This intelligent decision-making method for the operation mode of key wastewater treatment equipment, aimed at energy conservation and consumption reduction, focuses on dynamically optimizing equipment operating parameters through data-driven approaches. The method aims to establish a mapping relationship between water quality status, microbial aerobic behavior, and equipment energy supply strategies, breaking through the dependence of traditional control logic on static operating conditions. This allows the system to minimize ineffective energy consumption while ensuring effluent quality meets standards.

[0004] Some solutions attempt to introduce online water quality sensors (such as COD and NH4). + While closed-loop control systems (using N and DO probes) are constructed, they generally suffer from problems such as feedback lag, weak model generalization ability, and multivariate coupling interference. Especially under scenarios of sudden changes in influent load or seasonal temperature variations, a significant mismatch easily occurs between oxygen supply and the actual oxygen demand of microorganisms: insufficient oxygen supply inhibits nitrification, leading to excessive ammonia nitrogen; while excessive aeration not only wastes energy but also damages sludge settling performance and even causes ineffective carbon source consumption. Furthermore, existing control systems often isolate and adjust single devices, failing to comprehensively consider the synergistic effects between multiple devices such as aeration supply, internal recirculation, and stirring intensity, making it difficult to form a globally optimal operating strategy. Summary of the Invention

[0005] This invention provides an intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction. By integrating multi-source heterogeneous sensor data and process mechanism models, it constructs a dynamic prediction mechanism for oxygen demand based on real-time extrapolation of microbial metabolic state. Combined with the energy efficiency characteristic model of the aeration system, it generates operation instructions for aeration equipment that are precisely matched with the current biochemical reaction requirements, thereby solving the technical problem of dynamic mismatch between oxygen supply and microbial oxygen demand in the aeration system.

[0006] This invention provides an intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction, which includes:

[0007] Acquire multi-dimensional process sensing data within the wastewater treatment biochemical tank. The multi-dimensional process sensing data includes dissolved oxygen concentration, oxidation-reduction potential, ammonia nitrogen concentration, nitrate nitrogen concentration, sludge concentration, influent flow rate, influent chemical oxygen demand, and blower outlet pressure.

[0008] Based on the multi-dimensional process sensing data, the actual oxygen demand rate of the microorganisms at the current moment is calculated through the microbial metabolic activity state inference model.

[0009] Based on historical operating data and equipment performance curves, an energy efficiency characteristic model of the aeration system is constructed. The energy efficiency characteristic model of the aeration system characterizes the nonlinear mapping relationship between blower speed, valve opening degree and unit oxygen supply energy consumption.

[0010] The actual oxygen demand rate of the microorganisms is input into the oxygen demand analysis module to generate a target oxygen supply rate instruction.

[0011] The target oxygen supply rate command is jointly optimized and solved with the energy efficiency characteristic model of the aeration system to output the blower speed setting value and air regulating valve opening setting value that minimize the unit oxygen supply energy consumption and meet the oxygen supply accuracy constraint.

[0012] The blower speed setting value and the air regulating valve opening setting value are sent to the actuator to control the operation of the aeration equipment.

[0013] As one embodiment of the present invention, the acquisition of multi-dimensional process sensing data within the wastewater treatment biochemical tank specifically includes:

[0014] Dissolved oxygen concentration time-series data is obtained by a dissolved oxygen sensor installed in the mixed liquid of the biological treatment tank;

[0015] Oxidation-reduction potential signals reflecting the activity of the microbial electron transport chain are obtained using an oxidation-reduction potential sensor.

[0016] Ammonia nitrogen concentration and nitrate nitrogen concentration were obtained using an online ammonia nitrogen analyzer and a nitrate nitrogen analyzer, respectively.

[0017] The concentration of suspended solids in the mixed liquor was obtained using a sludge concentration meter.

[0018] The instantaneous flow rate of sewage entering the biological treatment tank is obtained by using an ultrasonic flow meter;

[0019] The organic load of the influent was obtained using an online chemical oxygen demand analyzer.

[0020] The pressure value of the main pipeline at the blower outlet is obtained through a pressure transmitter.

[0021] As one embodiment of the present invention, the construction process of the microbial metabolic activity state deduction model includes:

[0022] A substrate-limited microbial growth kinetics framework based on the Monod equation was established, and endogenous respiration and inhibition terms were introduced for correction.

[0023] The influent chemical oxygen demand, ammonia nitrogen concentration, and nitrate nitrogen concentration were used as external substrate input variables, and the sludge concentration was used as a biomass state variable.

[0024] By introducing redox potential as an indicator of electron acceptor availability, the relative growth rate of heterotrophic bacteria to autotrophic bacteria can be dynamically modulated.

[0025] The Kalman filter is used to correct the internal state variables of the model in real time, eliminating the cumulative error caused by sensor drift and model structural uncertainty.

[0026] Output the sum of the oxygen consumption rates of heterotrophic bacteria and autotrophic bacteria at the current moment, as the actual oxygen demand rate of the microorganisms.

[0027] As one embodiment of the present invention, the process of constructing the energy efficiency characteristic model of the aeration system includes:

[0028] During the shutdown and maintenance of the sewage treatment plant, a stepped load test was conducted on the blower at different speeds, and the corresponding air flow, outlet pressure and motor input power were recorded.

[0029] Throttling characteristics of the air regulating valve were tested at different opening degrees, and the pressure difference and flow rate before and after the valve were recorded.

[0030] The efficiency surface function of the blower is fitted based on the test data. The function takes the speed and outlet pressure as independent variables and the energy consumption per unit volume of air as the dependent variable.

[0031] Fit the nonlinear relationship function between the flow coefficient and the opening degree of the control valve;

[0032] By coupling the blower efficiency surface function with the regulating valve flow coefficient function, a complete energy efficiency characteristic model of the aeration system is formed. This model can back-calculate the optimal equipment operation combination based on the target oxygen supply rate.

[0033] As one embodiment of the present invention, the working logic of the oxygen demand analysis module includes:

[0034] Set a safe threshold range for dissolved oxygen concentration. When the measured dissolved oxygen concentration is lower than the lower limit of the range, activate the emergency oxygen supply compensation mechanism to directly increase the target oxygen supply rate.

[0035] When the measured dissolved oxygen concentration is within the safe threshold range, the actual oxygen demand rate of microorganisms is used as the base value of the target oxygen supply rate.

[0036] A feedforward compensation term is introduced, which is generated by filtering the product of influent flow rate and influent chemical oxygen demand through a first-order inertial link, and is used to respond in advance to sudden changes in influent load.

[0037] A rate of change constraint is imposed on the target oxygen supply rate to prevent frequent and large adjustments by the actuators and ensure system stability.

[0038] As one embodiment of the present invention, the joint optimization solution process adopts a hierarchical optimization strategy:

[0039] The outer layer optimization takes the minimum energy consumption per unit oxygen supply as the objective function, and the decision variables are the blower speed and the opening of the regulating valve. The constraints include the oxygen supply rate being equal to the target oxygen supply rate, the blower operating point being within the safe operating range, and the regulating valve opening being between 10% and 100%.

[0040] The inner layer optimization uses a lookup table method combined with bilinear interpolation to quickly locate the feasible solution set that meets the oxygen supply requirements in the data grid pre-stored in the energy efficiency characteristic model of the aeration system.

[0041] The outer optimization uses a sequential quadratic programming algorithm to search for the globally optimal operation point in the feasible solution set;

[0042] The optimization results are filtered and smoothed before being output as device control commands.

[0043] As one embodiment of the present invention, the method further includes an adaptive switching mechanism for operating modes:

[0044] When a drastic fluctuation in the influent water quality or abnormal sensor data is detected, the system automatically switches to a rule-based conservative operation mode, which is controlled according to a preset dissolved oxygen concentration-blower speed step table.

[0045] When the system runs continuously and stably for more than the preset time and the model residual is less than the threshold, it automatically switches back to the intelligent decision-making mode.

[0046] The switching process employs a non-disruptive switching strategy to ensure the continuity of control commands and a smooth transition of the actuators.

[0047] This invention provides an intelligent decision-making system for the operation modes of key wastewater treatment equipment aimed at energy conservation and consumption reduction, comprising:

[0048] A multi-source data acquisition unit is used to acquire multi-dimensional process sensing data within the wastewater treatment biochemical tank;

[0049] The microbial oxygen demand rate extrapolation unit is used to calculate the actual oxygen demand rate of microorganisms at the current moment based on the multi-dimensional process sensing data.

[0050] The aeration energy efficiency modeling unit is used to build and maintain the energy efficiency characteristic model of the aeration system;

[0051] The oxygen demand analysis unit is used to generate the target oxygen supply rate command.

[0052] The joint optimization decision unit is used to jointly optimize and solve the target oxygen supply rate command and the energy efficiency characteristic model of the aeration system, and output the blower speed setting value and the air regulating valve opening setting value.

[0053] The execution command issuing unit is used to transmit the blower speed setting value and the air regulating valve opening setting value to the field actuator.

[0054] As one embodiment of the present invention, the multi-source data acquisition unit is connected to the field instrument via industrial Ethernet, the sampling period is 10 seconds, and the data is stored in the real-time database after being timestamped.

[0055] The microbial aerobic rate simulation unit is deployed on an edge computing node and performs a state simulation every 30 seconds.

[0056] The aeration efficiency modeling unit receives equipment performance test data periodically and updates the model parameters monthly.

[0057] The optimization cycle of the joint optimization decision unit is 1 minute, and each optimization calculation takes no more than 15 seconds.

[0058] As one embodiment of the present invention, the system further includes a model health monitoring module, which continuously calculates the consistency index between the microbial aerobic rate projection results and the actual dissolved oxygen change trend. When the consistency index is lower than a preset threshold three times in a row, the model reconstruction process is triggered to re-identify the kinetic parameters.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0060] 1. This invention abandons the traditional feedback control strategy based on a fixed dissolved oxygen setpoint and realizes for the first time a paradigm shift from on-demand oxygen supply to precise matching of microbial metabolic needs.

[0061] 2. By constructing a model to predict the metabolic activity state of microorganisms, the actual oxygen demand rate of microorganisms can be quantified in real time, solving the problem of delayed or excessive oxygen supply caused by fluctuations in water quality and quantity. Simultaneously, by establishing an energy efficiency characteristic model of the aeration system and embedding it into the optimization decision framework, it is ensured that the system operates with the lowest possible energy consumption per unit of oxygen supply while meeting the needs of biochemical reactions.

[0062] 3. The system avoids operating the blower in its inefficient zone, significantly reducing energy consumption. The adaptive switching mechanism for operating modes ensures the system's robustness and safety under abnormal conditions. The overall solution achieves refined, intelligent, and energy-efficient control of the aeration process in wastewater treatment, reducing electricity consumption per ton of water by 12% to 18%, while simultaneously improving the stability of effluent quality, providing reliable technical support for wastewater treatment plants to achieve their carbon reduction targets. Attached Figure Description

[0063] Figure 1 This is a schematic diagram of the overall technical solution architecture of the intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction proposed in this invention.

[0064] Figure 2 This is a schematic diagram of the core principle framework of the dynamic prediction mechanism for oxygen demand based on real-time extrapolation of microbial metabolic state in this invention.

[0065] Figure 3 This is a logical flowchart of the multi-dimensional process sensing data acquisition and microbial oxygen demand rate extrapolation in this invention;

[0066] Figure 4 This is a diagram of the joint optimization decision-making framework for constructing the energy efficiency characteristic model of the aeration system and analyzing the oxygen supply demand in this invention;

[0067] Figure 5 This is a schematic diagram of the multi-level interaction relationship and data flow between the blower and the air regulating valve in this invention;

[0068] Figure 6 This is a logic control framework diagram of the adaptive switching mechanism for operating modes in this invention. Detailed Implementation

[0069] Please refer to Figures 1 to 6 This invention provides an intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction. Its core lies in constructing a dynamic oxygen demand prediction mechanism based on real-time extrapolation of microbial metabolic state by integrating multi-source heterogeneous sensor data and process mechanism models. Combined with an energy efficiency characteristic model of the aeration system, this generates aeration equipment operation commands that precisely match the current biochemical reaction requirements, thereby solving the technical problem of dynamic mismatch between oxygen supply and microbial oxygen demand in the aeration system. The specific implementation methods of this method will be described in detail below.

[0070] The method includes the following steps: acquiring multi-dimensional process sensing data within the wastewater treatment biochemical tank; calculating the actual oxygen demand rate of microorganisms at the current moment using a microbial metabolic activity state deduction model based on the multi-dimensional process sensing data; constructing an energy efficiency characteristic model of the aeration system based on historical operating data and equipment performance curves; inputting the actual oxygen demand rate of microorganisms into an oxygen supply demand analysis module to generate a target oxygen supply rate command; jointly optimizing and solving the target oxygen supply rate command and the energy efficiency characteristic model of the aeration system to output blower speed setpoints and air regulating valve opening setpoints that minimize unit oxygen supply energy consumption and meet oxygen supply accuracy constraints; and sending the blower speed setpoints and air regulating valve opening setpoints to the actuator to control the operation of the aeration equipment.

[0071] In step S1, multi-dimensional process sensing data is acquired within the wastewater treatment biological treatment tank. This multi-dimensional process sensing data includes dissolved oxygen concentration, oxidation-reduction potential, ammonia nitrogen concentration, nitrate nitrogen concentration, sludge concentration, influent flow rate, influent chemical oxygen demand, and blower outlet pressure. Specifically, dissolved oxygen concentration time-series data is acquired using a dissolved oxygen sensor installed in the mixed liquor of the biological treatment tank. This sensor employs the fluorescence quenching principle, sampling at a frequency of once every 10 seconds, and the output signal is converted from analog to digital and stored in a real-time database as a floating-point number. An oxidation-reduction potential sensor is used to acquire oxidation-reduction potential signals reflecting the activity of the microbial electron transport chain. This signal characterizes the availability of electron acceptors in the system and directly affects the metabolic pathway selection of heterotrophic and autotrophic bacteria.

[0072] Ammonia nitrogen concentration and nitrate nitrogen concentration were obtained using an online ammonia nitrogen analyzer and a nitrate nitrogen analyzer, respectively. Both analyzers employ the ion-selective electrode method, completing a full measurement cycle every 30 seconds, and a temperature compensation algorithm is used to eliminate the influence of environmental fluctuations. The concentration of suspended solids in the mixed liquor was obtained using a sludge concentration meter based on the principle of infrared light scattering. After calibration, the output value had an error of no more than 3% compared with the laboratory drying and weighing method. The instantaneous flow rate of wastewater entering the biological treatment tank was obtained using an ultrasonic flow meter installed on the main inlet pipeline. This flow meter uses a multi-channel cross-correlation algorithm, and the measurement accuracy is better than ±0.5%. The organic load of the inlet water was obtained using an online chemical oxygen demand (COD) analyzer. This analyzer uses the potassium dichromate oxidation-ultraviolet absorption method and outputs valid data points every 15 minutes.

[0073] The pressure value of the main outlet pipeline of the blower is obtained through a pressure transmitter with a range of 0 to 100 kPa and a resolution better than 10 Pa. The signal is then fed into the control system after anti-interference filtering. All the above data are immediately timestamped after acquisition and transmitted to the edge computing node via industrial Ethernet for initial alignment and integrity verification. Missing or abnormal data points are repaired by linear interpolation based on the valid values ​​before and after, ensuring the continuity and reliability of data in subsequent processing.

[0074] In step S2, based on the multi-dimensional process sensing data, the actual oxygen demand rate of the microorganisms at the current moment is calculated using a microbial metabolic activity state extrapolation model. The model construction process includes: establishing a substrate-limited microbial growth kinetic framework based on the Monod equation, introducing endogenous respiration and inhibition terms for correction; using influent chemical oxygen demand (COD), ammonia nitrogen concentration, and nitrate nitrogen concentration as external substrate input variables, and sludge concentration as a biomass state variable; introducing redox potential as an electron acceptor availability index to dynamically modulate the specific growth rate of heterotrophic and autotrophic bacteria; using a Kalman filter to correct the internal state variables of the model in real time, eliminating accumulated errors caused by sensor drift and model structural uncertainties; and outputting the sum of the oxygen consumption rates of heterotrophic and autotrophic bacteria at the current moment as the actual oxygen demand rate of the microorganisms. Specifically, the specific growth rate of heterotrophic bacteria... Determined by the following formula:

[0075] ,

[0076] in, This represents the maximum specific growth rate of heterotrophic bacteria. The concentration of biodegradable chemical oxygen demand. Its half-saturation constant, Dissolved oxygen concentration, is the half-saturation constant of oxygen for heterotrophic bacteria. This refers to the concentration of nitrate nitrogen. Its inhibition constant. Specific growth rate of autotrophic bacteria (mainly nitrifying bacteria). Determined by the following formula:

[0077] ,

[0078] in, This represents the maximum specific growth rate of autotrophic bacteria. This refers to the ammonia nitrogen concentration. Its half-saturation constant, This represents the half-saturation constant of oxygen for autotrophic bacteria. The redox potential is used to dynamically adjust the effective dissolved oxygen concentration in the above equation. When the redox potential falls below a preset threshold (e.g., -100 mV), it indicates that the system is in a hypoxic or anaerobic state. In this case, even if the dissolved oxygen reading is not zero, it is considered an ineffective oxygen source, and the model automatically... Set the value to 0. Actual oxygen demand rate of microorganisms. Calculated by the following formula:

[0079] ,

[0080] in, and These are the yield coefficients for heterotrophic and autotrophic bacteria, respectively. and Its biomass concentration (allocated from the total sludge concentration according to an empirical ratio). and The endogenous respiration attenuation coefficient is denoted as . The model performs a state simulation every 30 seconds. The Kalman filter corrects the internal state variables $X_H$ and $X_A$ online based on the measured trend of dissolved oxygen concentration. The correction gain is dynamically adjusted by the covariance matrix to ensure that the simulation results are highly consistent with the actual biochemical reaction process.

[0081] In step S3, an energy efficiency characteristic model of the aeration system is constructed based on historical operating data and equipment performance curves. This model characterizes the nonlinear mapping relationship between blower speed, valve opening, and unit oxygen supply energy consumption. The construction process includes: conducting stepped load tests on the blower at different speeds during the sewage treatment plant's shutdown and maintenance, recording the corresponding airflow, outlet pressure, and motor input power; conducting throttling characteristic tests on the air regulating valve at different openings, recording the pressure difference and flow rate before and after the valve; fitting a blower efficiency surface function based on the test data, with speed and outlet pressure as independent variables and energy consumption per unit volume of air as the dependent variable; fitting a nonlinear relationship function between the regulating valve flow coefficient and opening; and coupling the blower efficiency surface function and the regulating valve flow coefficient function to form a complete energy efficiency characteristic model of the aeration system. Specifically, the blower's unit oxygen supply energy consumption... It can be expressed by the following formula:

[0082] ;

[0083] in, This refers to the blower speed (revolutions per minute). Export pressure (kPa). Input electrical power (kilowatts) to the motor. This is the air volumetric flow rate (cubic meters per hour). The function is constructed using three-dimensional spline interpolation on a preset grid of points, covering a rotational speed range of 600 to 3000 revolutions per minute and a pressure range of 20 to 80 kPa. (The last phrase appears to be unrelated and likely refers to a control valve's flow rate.) Its opening and pressure difference The relationship is:

[0084] ;

[0085] in, The flow coefficient is obtained through polynomial fitting: u represents the valve opening percentage (10% to 100%). Total oxygen supply rate of the aeration system. With airflow The relationship is ,in The conversion factor for oxygen content in the air is 0.21. The energy efficiency characteristic model is updated monthly to incorporate the effects of equipment aging and environmental changes.

[0086] In step S4, the actual oxygen demand rate of the microorganisms is input to the oxygen demand analysis module to generate a target oxygen supply rate command. The module's operating logic includes: setting a safe dissolved oxygen concentration threshold range of 1.5 to 3.0 mg / L; when the measured dissolved oxygen concentration is below 1.5 mg / L, an emergency oxygen supply compensation mechanism is activated, increasing the target oxygen supply rate to 150% of the actual oxygen demand rate of the microorganisms; when the measured dissolved oxygen concentration is within the safe threshold range, the actual oxygen demand rate of the microorganisms is used as the base value for the target oxygen supply rate; introducing a feedforward compensation term, which is generated by filtering the product of the influent flow rate and the influent chemical oxygen demand through a first-order inertial loop, with a time constant set to 300 seconds, to respond in advance to sudden changes in influent load; imposing a rate-of-change constraint on the target oxygen supply rate, with a maximum allowable rate of change of 10% per minute, to prevent frequent and significant adjustments by the actuators and ensure system stability. The final target oxygen supply rate command is then generated. for:

[0087] ;

[0088] in, For feedforward gain, This refers to the inlet water flow rate. Chemical oxygen demand (COD) of the influent. The filtering time constant is It is a rate-of-change limiter.

[0089] In step S5, the target oxygen supply rate command and the energy efficiency characteristic model of the aeration system are jointly optimized and solved to output the blower speed set value and air regulating valve opening set value that minimize the unit oxygen supply energy consumption and meet the oxygen supply accuracy constraint. This process adopts a hierarchical optimization strategy: the outer layer optimization takes the minimum unit oxygen supply energy consumption as the objective function, the decision variables are the blower speed n and the regulating valve opening u, and the constraints include the oxygen supply rate being equal to the target oxygen supply rate, the blower operating point being within the safe operating range, and the regulating valve opening being between 10% and 100%; the inner layer optimization uses a lookup table method combined with bilinear interpolation to quickly locate the feasible solution set that meets the oxygen supply requirements in the data grid pre-stored in the energy efficiency characteristic model of the aeration system; the outer layer optimization uses a sequential quadratic programming algorithm to search for the globally optimal operating point in the feasible solution set; the optimization results are filtered by dead zone (dead zone width is speed ±5 revolutions per minute, opening ±0.5%) and smoothed by first order (time constant 60 seconds) before being output as equipment control commands. The optimization cycle is 1 minute, and each calculation takes no more than 15 seconds to ensure real-time performance.

[0090] In step S6, the blower speed setpoint and air regulating valve opening setpoint are sent to the actuator to control the operation of the aeration equipment. The commands are transmitted to the frequency converter and electric actuator via the industrial fieldbus protocol, and the actuator provides feedback on the actual operating status for closed-loop verification.

[0091] In addition, the method also includes an adaptive switching mechanism for operating modes: when a drastic fluctuation in the influent water quality is detected (such as a sudden change in the influent chemical oxygen demand exceeding 50%) or abnormal sensor data is detected (such as dissolved oxygen readings exceeding the physical reasonable range three times in a row), it automatically switches to a rule-based conservative operating mode. This mode is controlled according to a preset dissolved oxygen concentration-blower speed gradient reference table, which includes 5 dissolved oxygen ranges and their corresponding fixed speed settings. When the system has been running stably for more than 24 hours and the model residual (i.e., the deviation between the projected oxygen demand rate and the actual oxygen supply rate) is less than 5%, it automatically switches back to the intelligent decision-making mode. The switching process adopts a disturbance-free switching strategy, with the old and new commands connected through a linear transition section with a transition time of 300 seconds, ensuring the continuity of control commands and the smooth transition of the actuator.

[0092] In summary, this embodiment achieves precise, efficient, and robust control of the wastewater treatment aeration process through the above six core steps and auxiliary mechanisms, significantly reducing energy consumption while ensuring the stability of effluent water quality.

Claims

1. An intelligent decision-making method for the operation mode of key wastewater treatment equipment aimed at energy conservation and consumption reduction, characterized in that, include: Acquire multi-dimensional process sensing data within the wastewater treatment biochemical tank. The multi-dimensional process sensing data includes dissolved oxygen concentration, oxidation-reduction potential, ammonia nitrogen concentration, nitrate nitrogen concentration, sludge concentration, influent flow rate, influent chemical oxygen demand, and blower outlet pressure. Based on the multi-dimensional process sensing data, the actual oxygen demand rate of the microorganisms at the current moment is calculated through the microbial metabolic activity state inference model. Based on historical operating data and equipment performance curves, an energy efficiency characteristic model of the aeration system is constructed. The energy efficiency characteristic model of the aeration system characterizes the nonlinear mapping relationship between blower speed, valve opening degree and unit oxygen supply energy consumption. The actual oxygen demand rate of the microorganisms is input into the oxygen demand analysis module to generate a target oxygen supply rate instruction. The target oxygen supply rate command is jointly optimized and solved with the energy efficiency characteristic model of the aeration system to output the blower speed setting value and air regulating valve opening setting value that minimize the unit oxygen supply energy consumption and meet the oxygen supply accuracy constraint. The blower speed setting value and the air regulating valve opening setting value are sent to the actuator to control the operation of the aeration equipment.

2. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 1, is characterized in that... Acquire multi-dimensional process sensing data within the wastewater treatment biological treatment tank, including: Dissolved oxygen concentration time-series data is obtained by a dissolved oxygen sensor installed in the mixed liquid of the biological treatment tank; Oxidation-reduction potential signals reflecting the activity of the microbial electron transport chain are obtained using an oxidation-reduction potential sensor. Ammonia nitrogen concentration and nitrate nitrogen concentration were obtained using an online ammonia nitrogen analyzer and a nitrate nitrogen analyzer, respectively. The concentration of suspended solids in the mixed liquor was obtained using a sludge concentration meter. The instantaneous flow rate of sewage entering the biological treatment tank is obtained by using an ultrasonic flow meter; The organic load of the influent was obtained using an online chemical oxygen demand analyzer. The pressure value of the main pipeline at the blower outlet is obtained through a pressure transmitter.

3. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 2, is characterized in that... Based on the aforementioned multi-dimensional process sensing data, the actual oxygen demand rate of the microorganisms at the current moment is calculated using a microbial metabolic activity state extrapolation model, including: A substrate-limited microbial growth kinetics framework based on the Monod equation was established, and endogenous respiration and inhibition terms were introduced for correction. The influent chemical oxygen demand, ammonia nitrogen concentration, and nitrate nitrogen concentration were used as external substrate input variables, and the sludge concentration was used as a biomass state variable. By introducing redox potential as an indicator of electron acceptor availability, the relative growth rate of heterotrophic bacteria to autotrophic bacteria can be dynamically modulated. The Kalman filter is used to correct the internal state variables of the model in real time, eliminating the cumulative error caused by sensor drift and model structural uncertainty. Output the sum of the oxygen consumption rates of heterotrophic bacteria and autotrophic bacteria at the current moment, as the actual oxygen demand rate of the microorganisms.

4. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction as described in claim 3, characterized in that, Based on historical operating data and equipment performance curves, an energy efficiency characteristic model of the aeration system is constructed, including: During the shutdown and maintenance of the sewage treatment plant, a stepped load test was conducted on the blower at different speeds, and the corresponding air flow, outlet pressure and motor input power were recorded. Throttling characteristics of the air regulating valve were tested at different opening degrees, and the pressure difference and flow rate before and after the valve were recorded. The efficiency surface function of the blower is fitted based on the test data. The function takes the speed and outlet pressure as independent variables and the energy consumption per unit volume of air as the dependent variable. Fit the nonlinear relationship function between the flow coefficient and the opening degree of the control valve; By coupling the blower efficiency surface function with the regulating valve flow coefficient function, a complete energy efficiency characteristic model of the aeration system is formed.

5. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 4, is characterized in that... The actual oxygen demand rate of the microorganisms is input into the oxygen demand analysis module to generate a target oxygen supply rate instruction, including: Set a safe threshold range for dissolved oxygen concentration. When the measured dissolved oxygen concentration is lower than the lower limit of the range, activate the emergency oxygen supply compensation mechanism to directly increase the target oxygen supply rate. When the measured dissolved oxygen concentration is within the safe threshold range, the actual oxygen demand rate of microorganisms is used as the base value of the target oxygen supply rate. A feedforward compensation term is introduced, which is generated by filtering the product of influent flow rate and influent chemical oxygen demand through a first-order inertial link, and is used to respond in advance to sudden changes in influent load. A rate of change constraint is imposed on the target oxygen supply rate to prevent frequent and large adjustments by the actuators and ensure system stability.

6. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 5, is characterized in that... The target oxygen supply rate command is jointly optimized and solved with the energy efficiency characteristic model of the aeration system to output the blower speed setpoint and air regulating valve opening setpoint that minimize the unit oxygen supply energy consumption and meet the oxygen supply accuracy constraint, including: The outer layer optimization takes the minimum energy consumption per unit oxygen supply as the objective function, and the decision variables are the blower speed and the opening of the regulating valve. The constraints include the oxygen supply rate being equal to the target oxygen supply rate, the blower operating point being within the safe operating range, and the regulating valve opening being between 10% and 100%. The inner layer optimization uses a lookup table method combined with bilinear interpolation to quickly locate the feasible solution set that meets the oxygen supply requirements in the data grid pre-stored in the energy efficiency characteristic model of the aeration system. The outer optimization uses a sequential quadratic programming algorithm to search for the globally optimal operation point in the feasible solution set; The optimization results are filtered and smoothed before being output as device control commands.

7. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction as described in claim 6, characterized in that, The blower speed setpoint and air regulating valve opening setpoint are sent to the actuator to control the operation of the aeration equipment, including: The blower speed setting value is transmitted to the frequency converter via the industrial fieldbus protocol, and the air regulating valve opening setting value is transmitted to the electric actuator. It receives feedback on the actual operating status from the actuator, which is used for closed-loop verification and instruction correction.

8. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 7, is characterized in that... The method also includes an adaptive switching mechanism for operating modes, including: When a drastic fluctuation in the influent water quality or abnormal sensor data is detected, the system automatically switches to a rule-based conservative operation mode, which is controlled according to a preset dissolved oxygen concentration-blower speed step table. When the system runs continuously and stably for more than the preset time and the model residual is less than the threshold, it automatically switches back to the intelligent decision-making mode. The switching process employs a non-disruptive switching strategy to ensure the continuity of control commands and a smooth transition of the actuators.

9. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction as described in claim 8, characterized in that, In the aforementioned adaptive switching mechanism for operating modes, the criteria for determining drastic fluctuations in influent water quality are: a sudden change in influent chemical oxygen demand exceeding 50%; and the criteria for determining abnormal sensor data are: dissolved oxygen readings exceeding the physically reasonable range three times consecutively.

10. The intelligent decision-making method for the operation mode of key wastewater treatment equipment oriented towards energy conservation and consumption reduction, as described in claim 9, is characterized in that... The model residual is the relative deviation between the estimated value of the actual oxygen demand rate of microorganisms and the measured value of the actual oxygen supply rate. The preset duration is 24 hours and the threshold is 5%.

Images