CN-121974482-A - Sewage treatment aeration system energy-saving optimal control method and system based on multi-source information fusion

CN121974482ACN 121974482 ACN121974482 ACN 121974482ACN-121974482-A

Abstract

The invention relates to the field of sewage treatment, and discloses an energy-saving optimization control method and system for a sewage treatment aeration system based on multi-source information fusion, wherein the method firstly collects water quality and water quantity of inlet water, biological pond environment and external electricity price signals in real time; then dynamically calculating a dissolved oxygen set value through a threshold weight rule model based on the water inlet parameter, taking the dissolved oxygen set value as a feedforward target to generate a preliminary control instruction, and carrying out feedback fine adjustment by combining the actual dissolved oxygen value in the pool; the method and the device realize advanced accurate control of aeration requirements and online optimization of running cost, effectively overcome the problems of lag of traditional control response and high energy consumption, remarkably improve the stability of the water quality of the effluent and reduce energy consumption.

Inventors

Zhao Jiongrong
YE JIAKANG
ZHANG FANGZHOU
Yan Shugen
XIAO XUEWEI
CHEN JIANFA
Yi Wanpeng

Assignees

深圳市善德环境(集团)有限公司

Dates

Publication Date: 20260505
Application Date: 20251217

Claims (10)

1. The energy-saving optimization control method for the sewage treatment aeration system based on multi-source information fusion is characterized by comprising the following steps of: s1, acquiring water quality parameters, water inflow flow parameters, environment parameters in a biological pond and external electricity price signals in real time; S2, calculating a dynamic dissolved oxygen set value in real time by presetting a dynamic calculation model based on the inlet water quality parameter and the inlet water flow parameter; S3, a feedforward-feedback composite control step, wherein the dynamic dissolved oxygen set value is used as a feedforward control target to generate a preliminary fan control instruction, and the preliminary fan control instruction is subjected to feedback fine adjustment based on the deviation between the actual dissolved oxygen measured value in the environmental parameter in the biological pond and the dynamic dissolved oxygen set value to generate a final fan control instruction; S4, an economic optimization step, namely dynamically adjusting control parameters in the feedforward-feedback composite control step on the premise of ensuring that the quality of the effluent reaches the standard. ; s5, executing the step, and sending the optimized final fan control instruction to a fan frequency converter so as to adjust the aeration quantity.
2. The energy-saving optimization control method for the sewage treatment aeration system based on multi-source information fusion according to claim 1, wherein the step of calculating the dynamic dissolved oxygen set value specifically comprises the following steps: based on the inflow COD concentration and inflow flow, the inflow COD load is calculated, and the calculation formula is as follows: COD_load = COD Flow 0.001; the COD is the concentration of COD in water, the unit is mg/L, the Flow is the water inflow Flow, the unit is m3/h, and the COD_load is the COD load, the unit is kg/h; based on the COD_load and combined with the influent ammonia nitrogen concentration NH3_N, the water temperature T and the influent total nitrogen concentration TN, calculating the dynamic dissolved oxygen set value DO_set through a rule model based on a threshold weight, wherein a calculation formula is as follows: DO_set = BASE_DO + W_cod + W_nh + W_temp + W_tn; wherein, the ammonia nitrogen concentration NH3_N of the inlet water, the water temperature T and the total nitrogen concentration TN of the inlet water are all parameters acquired in real time through the step S1; Wherein, BASE_DO is a preset basic dissolved oxygen value, W_cod, W_nh, W_temp and W_tn are weight values corresponding to COD load, ammonia nitrogen concentration, water temperature and total nitrogen concentration respectively; Wherein, each weight value is obtained from a preset weight array after comparing the real-time value of the corresponding parameter with the preset threshold array; And performing clipping processing on the DO_set obtained by calculation to ensure that the DO_set meets the following conditions: MIN_DO ≤ DO_set ≤ MAX_DO; Wherein MIN_DO and MAX_DO are preset lower and upper limits of the dissolved oxygen set point.
3. The energy-saving optimization control method for the sewage treatment aeration system based on multi-source information fusion according to claim 2, wherein the determining method for the weight values w_cod, w_nh, w_temp and w_tn is as follows: the actual value X of the parameter is compared with a set of increasing thresholds T1, T2, T3, and the weight index idx is determined according to the following equation: If X is greater than or equal to T3, idx=3 If X is greater than or equal to T2, idx=2 If X is greater than or equal to T1, idx=1 Otherwise idx=0 And according to the weight index idx, the weight value W=W [ idx ] is taken out from the corresponding weight arrays W0, W1, W2 and W3.
4. The energy-saving optimization control method for a sewage treatment aeration system based on multi-source information fusion according to claim 3, wherein the economic optimization step is realized by constructing and optimizing a multi-objective rewarding function, and the expression of the multi-objective rewarding function R is as follows: R = W 1 ·R_quality + W 2 ·R_energy + W 3 ·R_stability; wherein R_quality is a water quality rewarding item, R_energy is an energy consumption rewarding item, R_stability is a stability rewarding item, and W 1 、W 2 、W 3 is a dynamically adjusted weight coefficient; the calculation formula of the water quality rewarding item R_quality is as follows: R_quality = - Σi [λi × max(0, C_{i,out} - C_{i,standard})2 ]; Wherein λi is the weight coefficient of the ith water quality index, C_ { i, out } is the water outlet concentration of the ith index, and C_ { i, standard } is the emission standard limit value of the ith index; the calculation formula of the energy consumption rewarding item R_energy is as follows: R_energy = - P_total / P_baseline; Wherein P_total is the real-time total power consumption of the aeration system, and P_baseline is the reference power consumption; the calculation formula of the stability bonus term R_stability is as follows: R_stability = - Σj |DO_j - DO_{target,j}|; Wherein DO_j is the actual dissolved oxygen value of the jth monitoring point, DO_ { target, j } is the target dissolved oxygen value of the jth monitoring point; Dynamically adjusting the weight coefficient W 1 、W 2 、W 3 according to the real-time electricity price signal, lifting the weight of W 2 in the electricity price peak period and lifting the weights of W 1 and W 3 in the electricity price valley period; The weight coefficient W 2 increases when the real-time electricity rate is higher than the set proportion of the average electricity rate, and the weight coefficient W 1 and/or W 3 increases when the real-time electricity rate is lower than the set proportion of the average electricity rate.
5. The energy-saving optimization control method for the sewage treatment aeration system based on multi-source information fusion according to claim 2, wherein the parameters of the dynamic calculation model are updated on line through a parameter self-adaptive mechanism; The parameter self-adaptive mechanism is triggered when the prediction error of the model exceeds a set threshold value, and updates the model parameter vector theta according to a gradient descent method, wherein the updating formula is as follows: θ_{t+1} = θ_t - η × ∇J(θ_t); where θ_t is a model parameter vector at time t, η is a learning rate, J (θ) is a performance evaluation function constructed with a prediction error, ∇ J (θ_t) is a gradient of the performance function at θ_t.
6. The method for optimizing control of energy conservation of a sewage treatment aeration system based on multi-source information fusion according to claim 1, further comprising the steps of fault diagnosis and self-recovery: calculating the anomaly score of the sensor data, wherein the formula is as follows: Anomaly_score = |X_measured - X_expected| / σ; Wherein X_measured is a measured value of the sensor, X_expected is an expected value based on a process model or adjacent sensor data, and sigma is a standard deviation of the parameter history data; When the anomaly score exceeds a set threshold, judging that the sensor fails, and triggering a self-recovery mechanism; The self-recovery mechanism comprises the steps of starting a standby sensor and/or estimating fault point data through interpolation based on measured values of adjacent normal sensors, wherein an estimation formula is as follows: X_fault = (X_adjacent1 + X_adjacent2) / 2; and reduce the weight of the fault region in the control decisions.
7. The method for optimizing and controlling energy conservation of a sewage treatment aeration system based on multi-source information fusion according to claim 1, which is characterized by being implemented by adopting a cloud-edge cooperative architecture; the cloud server layer is responsible for periodically collecting historical operation data, and carrying out re-fitting optimization on parameters in the dynamic calculation model based on a regression analysis method, wherein the regression model is in the form of: DO_set= β 0 + β 1 ×NH3_N + β 2 ×COD_load + β 3 ×T + β 4 ×TN + β 5 ×Flow; Wherein beta 0 is the intercept, beta 1 to beta 5 are regression coefficients, and the regression coefficients are obtained through least square fitting; The edge computing layer is responsible for executing the method steps of any one of claims 1 to 6 in real time and receiving optimized model parameters from the cloud server layer.
8. The energy-saving optimization control method for the sewage treatment aeration system based on multi-source information fusion according to claim 1, wherein the feedback fine adjustment is realized by a PID controller, the input is dissolved oxygen deviation e (t) =do_set-do_measured, and the calculation formula of the output u (t) is: u(t) = K_p e(t) + K_i ∫e(τ)dτ + K_d (de(t)/dt); Wherein, K_p, K_i and K_d are respectively proportional, integral and differential coefficients.
9. The method of claim 1, further comprising, after the performing step, an effect evaluation and parameter adjustment step of: Monitoring the water quality index of the effluent and the energy consumption of the system in real time; Based on the monitoring result, evaluating the performance of the current control strategy; And dynamically adjusting control parameters in the feedforward-feedback composite control step or the economic optimization step according to the performance evaluation result.
10. A sewage treatment aeration energy saving optimization control system based on the method of any one of claims 1 to 9, comprising: a data aware layer comprising: The water inlet monitoring unit is arranged at the water inlet of the biological pond and used for collecting water quality parameters and water inlet flow parameters in real time, wherein the water inlet monitoring unit at least comprises a water inlet COD (chemical oxygen demand) online analyzer, a water inlet ammonia nitrogen online analyzer, a water inlet total nitrogen online analyzer and a water inlet flowmeter; the process monitoring unit is arranged in the biological pond and is used for collecting environmental parameters in the biological pond in real time and at least comprises a water temperature sensor, a pH sensor and a plurality of dissolved oxygen sensors distributed at the head end, the middle part and the tail end of the aerobic pond; The energy consumption and external data interface unit is used for collecting energy consumption data of the wind turbine and receiving real-time electricity price signals of an external power grid; The intelligent control layer is in communication connection with the data perception layer, and comprises a Programmable Logic Controller (PLC) in which a computer program is stored, and the computer program is used for: calculating a dynamic dissolved oxygen set value in real time through a preset dynamic calculation model based on the inflow water quality parameter and inflow water flow parameter from the data sensing layer; Generating a preliminary fan control instruction by taking the dynamic dissolved oxygen set value as a feedforward control target, and performing feedback fine adjustment on the preliminary fan control instruction based on the deviation between the actual dissolved oxygen measured value from the process monitoring unit and the dynamic dissolved oxygen set value to generate a final fan control instruction; on the premise of ensuring that the effluent quality reaches the standard, adjusting a control strategy of an aeration system according to the real-time electricity price signal from the energy consumption and external data interface unit; and the execution layer is in communication connection with the intelligent control layer and comprises a fan frequency converter and/or an air regulating valve, and is used for receiving the final fan control instruction issued by the intelligent control layer, and regulating the rotating speed of the fan and the opening degree of the valve so as to control the aeration quantity input into the biological pond.

Description

Sewage treatment aeration system energy-saving optimal control method and system based on multi-source information fusion Technical Field The invention relates to the field of sewage treatment, in particular to an energy-saving optimization control method and system for a sewage treatment aeration system based on multi-source information fusion. Background In the sewage treatment process of the activated sludge process, an aeration system is a core unit of aerobic biological treatment, and the energy consumption of the aeration system is about 50-70% of the total energy consumption of the whole sewage treatment plant. Therefore, the control precision and the operation efficiency of the aeration system are directly related to the stable standard of the effluent quality and the operation cost of the whole plant. Currently, most sewage treatment plant aeration systems employ a single loop PID control strategy based on a fixed dissolved oxygen (Dissolved Oxygen, DO) setpoint. In the strategy, a DO on-line monitoring instrument is arranged at the tail end of an aerobic zone of a biological tank, a controller compares the detected actual DO value with a manually set fixed value (generally 1.5-2.5 mg/L), and the rotating speed of a fan or the opening degree of a valve is regulated through a PID algorithm so that the actual DO value is maintained near the set value. However, the method has serious lag in response, poor capability of coping with impact load, and long hydraulic retention time of sewage in a biological pond for several hours. When the inflow water flow and the water quality (such as COD and ammonia nitrogen) have severe fluctuation (impact load), the DO value change can be caused only when pollutants need to flow to a DO monitoring point at the downstream, the controller adjusts according to the DO value change, and the whole system has hysteresis of a plurality of hours. This results in the biological pool being in an "unhealthy" condition for a long period of time during impact loading, which may cause fluctuations or even overstock in effluent quality. And the control is extensive, the energy waste is remarkable, and the fixed DO set value cannot adapt to the dynamic change of the water inlet load. Maintaining a high DO setpoint during the night or low load periods can result in excessive aeration and a large amount of electrical energy being wasted on unnecessary oxygen supplies, and during peak daytime load periods, a fixed DO setpoint may not be sufficient to meet the oxygen demand of the microorganism degrading contaminants, resulting in inadequate treatment. Disclosure of Invention In order to solve at least one technical problem, the invention provides an energy-saving optimization control method and system for a sewage treatment aeration system based on multi-source information fusion. In order to achieve the purpose, the invention provides an energy-saving optimization control method and system for a sewage treatment aeration system based on multi-source information fusion, and the specific technical scheme is as follows. A sewage treatment aeration system energy-saving optimization control method based on multi-source information fusion comprises the following steps: s1, acquiring water quality parameters, water inflow flow parameters, environment parameters in a biological pond and external electricity price signals in real time; S2, calculating a dynamic dissolved oxygen set value in real time by presetting a dynamic calculation model based on the inlet water quality parameter and the inlet water flow parameter; S3, a feedforward-feedback composite control step, wherein the dynamic dissolved oxygen set value is used as a feedforward control target to generate a preliminary fan control instruction, and the preliminary fan control instruction is subjected to feedback fine adjustment based on the deviation between the actual dissolved oxygen measured value in the environmental parameter in the biological pond and the dynamic dissolved oxygen set value to generate a final fan control instruction; S4, an economic optimization step, namely dynamically adjusting control parameters in the feedforward-feedback composite control step on the premise of ensuring that the quality of the effluent reaches the standard. ; s5, executing the step, and sending the optimized final fan control instruction to a fan frequency converter so as to adjust the aeration quantity. Further, the step of calculating the dynamic dissolved oxygen set value specifically includes: based on the inflow COD concentration and inflow flow, the inflow COD load is calculated, and the calculation formula is as follows: COD_load = CODFlow0.001; the COD is the concentration of COD in water, the unit is mg/L, the Flow is the water inflow Flow, the unit is m3/h, and the COD_load is the COD load, the unit is kg/h; based on the COD_load and combined with the influent ammonia nitrogen concentration NH3_N, the water temperature T and the i