Multi-parameter intelligent cooperative control method for sewage treatment equipment

Abstract

The invention discloses a multi-parameter intelligent cooperative control method for sewage treatment equipment, and particularly relates to the technical field of sewage treatment automatic control. Corresponding process grading grades are divided by monitoring a physical filtering process, a biochemical reaction process and a solid-liquid separation process; a physical-biochemical process parameter mapping relation and a biochemical-solid-liquid separation process parameter mapping relation are constructed, and operation parameters of the subsequent process are automatically adjusted; monitoring controlled effluent quality parameters, calculating a final water quality comprehensive score, and optimizing parameter adjustment in each process according to a deviation analysis result; and finally carrying out sewage treatment knowledge base updating and system self-learning. According to the cross-process parameter mapping mechanism based on the multi-process scoring grade, the treatment effect of the upstream process is used as the feedforward signal of the downstream process, and the fundamental transformation from local optimization to global coordination is realized, so that the stability of the effluent quality is remarkably improved, and the continuous and stable standard reaching is ensured.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology for wastewater treatment, specifically to a multi-parameter intelligent collaborative control method for wastewater treatment equipment. Background Technology

[0002] Wastewater treatment includes an intelligent control platform. The main process involves fine-tuning the treatment steps based on real-time wastewater discharge data, thereby achieving the goal of rational resource coordination in the wastewater treatment process.

[0003] Existing wastewater treatment systems include selecting a key indicator in the wastewater as the control basis, adjusting a certain operating parameter in the wastewater treatment process based on the deviation between the monitored value and the set value of the indicator; summarizing operating rules under different working conditions based on long-term accumulated wastewater treatment operation experience; and realizing automatic control of wastewater treatment equipment by setting some simple logical judgment conditions, thereby realizing the control of the wastewater treatment system.

[0004] While existing wastewater treatment systems are equipped with intelligent control platforms capable of fine-tuning treatment steps based on real-time wastewater discharge conditions, they suffer from significant limitations. Traditional methods often employ single-parameter adjustment strategies, which struggle to achieve balanced coordination among parameters in the complex, multi-dimensional, and strongly coupled process of wastewater treatment. Relying on empirical rules makes it difficult to accurately determine the magnitude and timing of parameter adjustments. Simple logic control lacks a global optimization consideration of the entire wastewater treatment process, resulting in poor synergy between different treatment stages, particularly between physical, biochemical, and solid-liquid separation stages. This leads to low treatment efficiency, unreasonable resource allocation, and difficulty in coping with water quality fluctuations. Therefore, a multi-process coordinated intelligent control method for wastewater treatment equipment is needed to achieve optimal control throughout the entire wastewater treatment process. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a multi-parameter intelligent collaborative control method for sewage treatment equipment to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a multi-parameter intelligent collaborative control method for wastewater treatment equipment, comprising: S1: Collect monitoring parameters of the physical filtration process in wastewater treatment using data acquisition equipment, construct a mathematical model for physical filtration scoring, calculate the physical filtration treatment effect score, and classify the physical treatment score levels. S2: Through data acquisition equipment, collect monitoring parameters of the biochemical reaction process of wastewater treatment, construct a mathematical model for biochemical reaction scoring, calculate the biochemical reaction treatment effect score, and classify the biochemical reaction score level. S3: Collect monitoring parameters of the solid-liquid separation process in wastewater treatment through data acquisition equipment, construct a mathematical model for solid-liquid separation scoring, calculate the solid-liquid separation treatment effect score, and classify the solid-liquid separation score level. S4: Based on the scoring levels of physical filtration and biochemical reaction processes, construct the parameter mapping relationship between physical and biochemical processes and the parameter mapping relationship between biochemical and solid-liquid separation processes, and automatically adjust the operating parameters of subsequent processes through the control system to obtain the controlled effluent water quality parameters; S5: By monitoring the controlled effluent water quality parameters, calculate the final comprehensive water quality score, compare and analyze the deviation with the design value, establish a multi-process callback weight model to optimize the adjustment amount of each process parameter, and feed it back to the corresponding sewage treatment process equipment. S6: Record and store the data generated during the wastewater treatment process, update the wastewater treatment knowledge base, calculate and evaluate the wastewater treatment water quality improvement rate, optimize the model parameters using machine learning algorithms based on the abnormal evaluation results, and store the optimized model parameters in the wastewater treatment knowledge base.

[0007] The technical effects and advantages of this invention are as follows: 1. This invention uses a cross-process parameter mapping mechanism based on multi-process scoring levels to treat the treatment effect of upstream processes as a feedforward signal for downstream processes, achieving a fundamental shift from local optimization to global collaboration. This can smooth fluctuations in water quality and quantity, reduce periodic oscillations in treatment effects, and thus significantly improve the stability of effluent water quality, ensuring continuous and stable compliance with standards. 2. This invention constructs a multi-level precise scoring system based on mathematical models and a callback allocation model based on contribution weights, providing precise and scientific data support for control decisions, which helps to accurately add and reduce costs and increase efficiency; at the same time, it avoids energy waste and equipment damage caused by blind adjustments, and realizes refined operation of energy saving and consumption reduction. 3. This invention combines closed-loop control with machine learning algorithms, giving the system the ability to continuously evolve, making the control strategy increasingly aligned with actual working conditions, autonomously adjusting control parameters, and always maintaining the optimal operating state. This reduces reliance on human experience, lowers the difficulty of operation and maintenance, and realizes intelligent collaborative control of multiple parameters for sewage treatment equipment. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the overall process of the present invention.

[0009] Figure 2 This is a schematic diagram of the method flow of the present invention.

[0010] Figure 3 This is a schematic diagram illustrating the principle of cross-process parameter coordinated adjustment in this invention. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] Please see Figure 1 As shown, the present invention provides a multi-parameter intelligent collaborative control system for wastewater treatment equipment, including a physical filtration process monitoring module, a biochemical reaction process monitoring module, a solid-liquid separation process monitoring module, a cross-process parameter collaboration module, a wastewater treatment water quality assessment and feedback module, and a wastewater treatment knowledge base update and self-learning module.

[0013] This embodiment needs to specifically explain that the wastewater treatment equipment of the present invention includes a physical filtration process, a biochemical reaction process, and a solid-liquid separation process in the wastewater treatment process.

[0014] The physical filtration process monitoring module is connected to the biochemical reaction process monitoring module, the solid-liquid separation process monitoring module is connected to the cross-process parameter coordination module, the wastewater treatment water quality assessment and feedback module is connected to the three process monitoring modules, and the wastewater treatment knowledge base update and self-learning module is connected to all other modules.

[0015] Physical filtration process monitoring module: Through data acquisition equipment, it collects monitoring parameters of the physical filtration process in wastewater treatment, constructs a mathematical model for physical filtration scoring, calculates the physical filtration treatment effect score, classifies the physical treatment score level, and transmits it to the biochemical reaction process monitoring module. Biochemical reaction process monitoring module: Through data acquisition equipment, it collects monitoring parameters of the biochemical reaction process in wastewater treatment, constructs a mathematical model for biochemical reaction scoring, calculates the biochemical reaction treatment effect score, classifies the biochemical reaction score level, and transmits it to the solid-liquid separation process monitoring module. Solid-liquid separation process monitoring module: Through data acquisition equipment, it collects monitoring parameters of the solid-liquid separation process in wastewater treatment, calculates the solid-liquid separation treatment effect score based on the constructed solid-liquid separation scoring mathematical model, classifies the solid-liquid separation score level, and transmits it to the cross-process parameter collaboration module; Cross-process parameter coordination module: Based on the rating levels of physical filtration process and biochemical reaction process, construct the physical-biochemical process parameter mapping relationship and the biochemical-solid-liquid separation process parameter mapping relationship, and automatically adjust the operating parameters of subsequent processes through the control system, and transmit the controlled effluent water quality parameters to the wastewater treatment water quality assessment and feedback module. Wastewater treatment water quality assessment and feedback module: By monitoring the controlled effluent water quality parameters, the final comprehensive water quality score is calculated, the deviation is analyzed by comparing with the design value, a multi-process callback weight model is established, the adjustment amount of parameters in each process is optimized, and the feedback is fed back to the monitoring module of each process. Wastewater Treatment Knowledge Base Update and Self-Learning Module: Records and stores data generated during the wastewater treatment process, updates the wastewater treatment knowledge base, calculates and evaluates the wastewater treatment water quality improvement rate, optimizes model parameters using machine learning algorithms based on abnormal evaluation results, and stores the optimized model parameters in the wastewater treatment knowledge base.

[0016] Please see Figure 2 As shown, a multi-parameter intelligent collaborative control method for wastewater treatment equipment includes: S1: Collecting monitoring parameters of the physical filtration process of wastewater treatment using data acquisition equipment, constructing a mathematical model for physical filtration scoring, calculating the physical filtration treatment effect score, and classifying the physical treatment score levels; S2: Collecting monitoring parameters of the biochemical reaction process of wastewater treatment using data acquisition equipment, constructing a mathematical model for biochemical reaction scoring, calculating the biochemical reaction treatment effect score, and classifying the biochemical reaction score levels; S3: Collecting monitoring parameters of the solid-liquid separation process of wastewater treatment using data acquisition equipment, constructing a mathematical model for solid-liquid separation scoring, calculating the solid-liquid separation treatment effect score, and classifying the solid-liquid separation score levels; S4: Based on the physical filtration process and the biochemical reaction process... The system assigns a rating to the chemical reaction process, constructs a mapping relationship between physical-biochemical process parameters and a mapping relationship between biochemical-solid-liquid separation process parameters, and automatically adjusts the operating parameters of subsequent processes through a control system to obtain the controlled effluent water quality parameters; S5: By monitoring the controlled effluent water quality parameters, the final comprehensive water quality score is calculated, and the deviation is analyzed by comparing it with the design value. A multi-process callback weight model is established to optimize the adjustment amount of each process parameter and feeds it back to the corresponding wastewater treatment process equipment; S6: The data generated in the wastewater treatment process is recorded and stored, the wastewater treatment knowledge base is updated, and the wastewater treatment water quality improvement rate is calculated and evaluated. Based on the evaluation anomaly results, machine learning algorithms are used to optimize the model parameters, and the optimized model parameters are stored in the wastewater treatment knowledge base.

[0017] S1: Using data acquisition equipment, collect monitoring parameters of the physical filtration process in wastewater treatment, construct a mathematical model for physical filtration scoring, calculate the physical filtration treatment effect score, and classify the physical treatment score levels, including the following steps: S1.1: Monitoring Parameter Acquisition: Through data acquisition equipment, the monitoring parameters of the physical filtration process of wastewater treatment are collected, including influent flow rate Q, influent suspended solids concentration SS0, influent turbidity NTU0, influent oil content OIL0, suspended solids concentration SS1 after physical filtration, turbidity NTU1 after physical filtration, oil content OIL1 after physical filtration, and membrane pressure difference ΔP. In this embodiment, it should be specifically noted that the data acquisition equipment uses an electromagnetic flowmeter to monitor the influent flow rate Q; a laser scattering suspended solids sensor to monitor SS0 and SS1; a turbidity meter to monitor NTU0 and NTU1; an infrared spectrophotometric oil analyzer to monitor OIL0 and OIL1; and a differential pressure transmitter to monitor the membrane pressure difference ΔP.

[0018] S1.2: Constructing a Mathematical Model for Physical Filtration Scoring: Based on the collected monitoring parameters of the physical filtration process in wastewater treatment, a mathematical model S1 for physical filtration scoring is constructed. S1 represents the physical filtration effect score, R ss R represents the suspended solids removal rate. ss =(SS0-SS1) / SS0, if SS0≤SS1, take R. ss =0, R NTU R represents the turbidity removal rate. ss =(NTU0-NTU1) / NTU0, if NTU0≤NTU1, take R. NTU =0, R OIL R represents the grease removal rate. OIL =(OIL0-OIL1) / OIL0, if OIL0≤OIL1, take R. OIL =0, ΔP max The maximum allowable membrane pressure difference for the membrane filtration system (provided by the membrane module manufacturer, typically 50-80 kPa) is defined by a1, a2, a3, and a4, which are the corresponding weighting coefficients. The values ​​for a1 range from 0.3 to 0.4, a2 from 0.25 to 0.35, a3 from 0.15 to 0.25, and a4 from 0.05 to 0.15. These values ​​are obtained through regression analysis of historical data. S1.3: Grading the physical treatment score: S1 is divided into 4 levels. If S1≥0.9, it indicates that the physical filtration treatment effect is excellent; if 0.8≤S1<0.9, it indicates that the physical filtration treatment effect is good; if 0.65≤S1<0.8, it indicates that the physical filtration treatment effect is moderate; if S1<0.65, it indicates that the physical filtration treatment effect is poor. S2: Using data acquisition equipment, collect monitoring parameters of the wastewater treatment biochemical reaction process, construct a mathematical model for biochemical reaction scoring, calculate the biochemical reaction treatment effect score, and classify the biochemical reaction score levels, including the following steps: S2.1: Monitoring Parameter Acquisition: Monitoring parameters of the wastewater treatment biochemical reaction process are collected using data acquisition equipment, including the influent COD concentration (COD_in, Chemical Oxygen Demand), the effluent COD concentration (COD_out1), and the influent ammonia nitrogen concentration (NH3). in effluent ammonia nitrogen concentration (NH3) out1The following parameters are measured: influent total nitrogen concentration (TN_in), effluent total nitrogen concentration (TN_out1), influent total phosphorus concentration (TP_in), effluent total phosphorus concentration (TP_out1), dissolved oxygen concentration (DO), mixed liquor suspended solids concentration (MLSS), pH value, reaction temperature (T), and sludge activity (SA) (obtained by dehydrogenase activity detection). This embodiment specifically illustrates the use of a potassium dichromate method COD online monitoring instrument to monitor COD_in and COD_out1; and a Nessler's reagent spectrophotometric online ammonia nitrogen analyzer to monitor NH3. in With NH3 out1 The following methods were used: UV spectrophotometric online total nitrogen analyzer to monitor TN_in and TN_out1; ammonium molybdate spectrophotometric online total phosphorus analyzer to monitor TP_in and TP_out1; fluorescence method dissolved oxygen sensor to monitor DO; laser scattering MLSS sensor to monitor MLSS; pH electrode to monitor pH value; platinum resistance temperature sensor to monitor T; and colorimetric method to detect sludge activity SA in the laboratory.

[0019] S2.2: Constructing a Mathematical Model for Biochemical Reaction Scoring: Based on the collected monitoring parameters of the wastewater treatment biochemical reaction process, a mathematical model S2 for biochemical reaction scoring is constructed. S2 represents the biochemical reaction treatment effect score, R COD R represents the COD removal rate. COD =(COD_in-COD_out1) / COD_in, if COD_in≤COD_in, take R COD =0, E nit E represents nitrification efficiency (the conversion of ammonia nitrogen to nitrate nitrogen). nit =(NH3 in -NH3 out1 ) / NH3 in If NH3 in ≤NH3 out1 Take E nit =0, E de For denitrification efficiency (converting nitrate nitrogen into nitrogen gas and releasing it into the atmosphere). If the numerator is 0, take E. de =0, R p For phosphorus removal efficiency, R p =(TP_in-TP_out1) / TP_in, if TP_in≤TP_out1, take R. p =0, SA maxThe maximum sludge activity is defined as 20-30 mg (g·h) and b1, b2, b3, b4, and b5 are the corresponding weighting coefficients. The values ​​of b1, b2, b3, b4, and b5 are 0.25-0.35, b2, b3, b4, and b5, respectively. S2.3: Grading of Biochemical Reaction Score: S2 is divided into 4 levels. If S2 ≥ 0.85, it indicates excellent biochemical reaction treatment effect; if 0.75 ≤ S2 < 0.85, it indicates good biochemical reaction treatment effect; if 0.6 ≤ S2 < 0.75, it indicates moderate biochemical reaction treatment effect; if S2 < 0.6, it indicates poor biochemical reaction treatment effect. S3: Using data acquisition equipment, collect monitoring parameters of the solid-liquid separation process in wastewater treatment, construct a mathematical model for solid-liquid separation scoring, calculate the solid-liquid separation treatment effect score, and classify the solid-liquid separation score levels, including the following steps: S3.1: Monitoring Parameter Acquisition: Monitoring parameters of the solid-liquid separation process in wastewater treatment are collected using data acquisition equipment, including the 30-minute settling ratio (SV). 30 Sludge volume index (SVI) and supernatant suspended solids concentration (SS) su Supernatant turbidity NTU_sup, sludge level height H_sl, and concentrated sludge concentration SS co ; This embodiment requires specific explanation regarding the use of a sedimentation ratio meter to monitor SV. 30 ; via SV 30 Calculate SVI with MLSS (SVI=SV) 30 ×10 / MLSS), Mixed liquor suspended solids concentration (MLSS) (representing the total mass of suspended solids per unit volume of mixed liquor in the aeration tank); Laser scattering suspended solids sensor monitors SS. su Turbidity meter monitoring NTU_sup; Ultrasonic mud level meter monitoring H_sl; Laboratory drying method for determining SS. co .

[0020] S3.2: Constructing a Mathematical Model for Solid-Liquid Separation Scoring: Based on the collected monitoring parameters of the solid-liquid separation process in wastewater treatment, a mathematical model S3 for solid-liquid separation scoring is constructed. ΔSV 30 To score the settlement ratio efficiency, SV 30,max and SV 30,opt These are the maximum allowable settling ratio (typically 50%) and the optimum settling ratio (typically 20%-30%), respectively. ΔSVI is the sludge volume index performance score. SVI max and SVIopt These are the maximum permissible SVI (typically 200 mL / g) and the optimal SVI (typically 100-150 mL / g), respectively, ΔSS su To ensure the compliance rate of suspended solids concentration in the supernatant, SS su,max ΔSS is the maximum allowable suspended solids concentration in the supernatant (typically 30 mg / L). co To improve the efficiency of concentrated sludge. SS co,max and SS in2 The maximum concentration of concentrated sludge (determined by equipment capacity, typically 10000-20000 mg / L) and the concentration of suspended solids in the solid-liquid separation influent (unit: mg / L) are calculated separately. c1, c2, c3, and c4 are the corresponding weighting coefficients, with c1 ranging from 0.25 to 0.35, c2 from 0.25 to 0.35, c3 from 0.2 to 0.3, and c4 from 0.1 to 0.2. S3.3: Grading of Solid-Liquid Separation Scoring: S3 is divided into 4 levels. If S3 ≥ 0.9, it indicates excellent solid-liquid separation treatment effect; if 0.8 ≤ S3 < 0.9, it indicates good solid-liquid separation treatment effect; if 0.6 ≤ S3 < 0.8, it indicates moderate solid-liquid separation treatment effect; if S3 < 0.6, it indicates poor solid-liquid separation treatment effect. Please see Figure 3 As shown, S4: Based on the rating levels of the physical filtration process and the biochemical reaction process, a mapping relationship between physical-biochemical process parameters and a mapping relationship between biochemical-solid-liquid separation process parameters are constructed. The operating parameters of subsequent processes are automatically adjusted through the control system to obtain the controlled effluent water quality parameters, including the following steps: S4.1: Establish a mapping relationship between physical and biochemical process parameters: If the physical filtration treatment effect score S1 ≥ 0.9, maintain the standard operating parameters of the biochemical reaction, including aeration rate A. b Carbon source addition amount C b and hydraulic residence time tt b If 0.8 ≤ S1 < 0.9, fine-tune the operating parameters of the biochemical reaction, including adjusting the aeration rate A1. af Adjusted carbon source dosage C1 af And the adjusted hydraulic residence time tt1 af A1 af =A b ×(1+5%), C1 af =C b ×(1-3%), tt1 af =tt b If 0.65 ≤ S1 < 0.8, further adjust the operating parameters of the biochemical reaction, including adjusting the aeration rate A2.af Adjusted carbon source dosage C2 af And the adjusted hydraulic residence time tt2 af A2 af =A b ×(1+10%), C2 af =C b ×(1-5%), tt2 af =tt b ×(1+5%); If S1<0.65, enhance the operating parameters of the biochemical reaction, including adjusting the aeration rate A3. af Adjusted carbon source dosage C3 af And the adjusted hydraulic residence time tt3 af A3 af =A b ×(1+15%), C3 af =C b ×(1-8%), tt3 af =tt b ×(1+10%); In this embodiment, it should be specifically noted that the standard operating parameters are a set of key operating parameters that remain unchanged from the original design or long-term operational verification at this stage, ensuring stable and satisfactory treatment results; the operating parameters refer to the aeration rate A. b Carbon source addition amount C b and hydraulic residence time t d Key operating parameters of the biochemical reaction process; increasing aeration rate enhances the metabolic activity of aerobic microorganisms, accelerates the degradation of residual organic matter, and thus improves COD removal efficiency; the physical stage has already removed a large amount of competing carbon sources, relatively reducing the carbon source required for denitrification; hydraulic retention time refers to the average residence time of wastewater in the biochemical reactor, determined by the effective volume of the biochemical reactor (m³). 3 ) and influent flow rate (m 3 The ratio of / h indicates that increasing the hydraulic retention time can prolong the contact time between wastewater and microorganisms, giving microorganisms more time to decompose wastewater, thereby improving the overall effect of biochemical reactions (such as COD and ammonia nitrogen removal rates). However, excessively long hydraulic retention times will reduce the equipment's processing load and increase infrastructure costs.

[0021] S4.2: Constructing the parameter mapping relationship for the biochemical-solid-liquid separation process: If the biochemical reaction treatment effect score S2 ≥ 0.85, maintain the standard operating parameters for solid-liquid separation, including the reflux ratio R. b Sludge discharge volume V b and sedimentation time ct b If 0.75 ≤ S2 < 0.85, fine-tune the solid-liquid separation operating parameters, including adjusting the reflux ratio R1. af Adjusted sludge discharge volume V1 af and adjusted sedimentation time ct1af R1 af =R b ×(1+5%), V1 af =V b ×(1-3%), tt1 af =ct b If 0.6 ≤ S2 < 0.75, further adjust the solid-liquid separation operating parameters, including the adjusted reflux ratio R2. af Adjusted sludge discharge volume V2 af and adjusted sedimentation time ct2 af R2 af =R b ×(1+10%), V2 af =V b ×(1-5%), tt2 af =ct b Add conventional flocculants at a dosage of 1-3 mg / L; if S2 < 0.6, enhance solid-liquid separation operating parameters, including adjusting the reflux ratio R3. af Adjusted sludge discharge volume V3 af and adjusted sedimentation time ct3 af R3 af =R b ×(1+15%), V3 af =V b ×(1-8%), tt3 af =ct b ×(1+20%), add enhanced flocculant, dosage 5-10mg / L; In this embodiment, it is necessary to specifically explain that the reflux ratio refers to the ratio of the amount of sludge refluxed from the solid-liquid separation unit (such as the secondary sedimentation tank) to the influent volume of the biological reaction tank. This determines that the higher the activated sludge concentration (MLSS) in the biological reaction tank, the stronger the ability of microorganisms to degrade pollutants. However, excessive MLSS will lead to poor sludge settling properties. The sludge discharge volume is the amount of residual sludge discharged from the solid-liquid separation unit (total sludge settled in the secondary sedimentation tank - sludge refluxed to the biological reaction tank). It is used to control the sludge age (the average residence time of sludge in the system). Reducing the sludge discharge volume can appropriately extend the sludge age, allowing the sludge to remain in the system for a longer period of time. The core function of flocculants (such as polyacrylamide, polyaluminum chloride, etc.) is to coagulate fine suspended solids and colloidal particles in wastewater into large flocs, thereby significantly improving the solid-liquid separation efficiency. The settling time is the time that wastewater stays in the solid-liquid separation unit, allowing the sludge flocs to settle fully. Increasing the settling time can give the flocs more sufficient settling time, ensuring that the suspended solids in the effluent meet the standards.

[0022] S5: By monitoring the controlled effluent water quality parameters, calculate the final comprehensive water quality score, compare and analyze the deviation with the design value, establish a multi-process callback weight model to optimize the adjustment of parameters in each process, and feed back to the corresponding wastewater treatment process equipment, including the following steps: S5.1: Calculate the final comprehensive water quality score: Monitor effluent water quality parameters, including effluent COD concentration. out effluent ammonia nitrogen concentration (NH3) out The final comprehensive water quality score S is calculated based on the effluent total phosphorus concentration TP_out and the effluent suspended solids concentration SS_out. fi S fi =d1×COD sc +d2×NH3 sc +d3×TP sc +d4×SS sc d1, d2, d3, and d4 are the corresponding weights. For example, d1=0.35, d2=0.3, d3=0.2, and d4=0.15 are the corresponding weights. sc To score for COD compliance, COD b The COD concentration limit is set according to local emission standards; the calculation logic for the other three water quality parameters is the same as that for COD. sc The corresponding local emission standards for ammonia nitrogen concentration (NH3) were adopted. b Total phosphorus concentration (TP) b and suspended solids concentration SS b Ammonia nitrogen compliance score (NH3) was obtained sc Total phosphorus (TP) score sc And suspended matter compliance score SS sc ; S5.2: Analytical Bias: Calculate the final comprehensive water quality score S fi The absolute difference from the design value (e.g., 0.9) is used to obtain the deviation value ΔS; then the callback strategy determines: if ΔS ≤ 0.05 (e.g., S... fi =0.85 or 0.95), adjustment range ≤5%; if 0.05 < ΔS ≤ 0.15, adjustment range 0.05 to 0.15; if ΔS > 0.15, adjustment range > 0.15 and the equipment operating status must be checked simultaneously (e.g., whether the membrane module is blocked, whether the aeration head is damaged). S5.3: Establish a multi-process callback weight model: First, calculate the absolute difference between the scores S1, S2, and S3 of each process and their corresponding design values ​​(e.g., the design value of S1 is 0.9, the design value of S2 is 0.85, and the design value of S3 is 0.9), and obtain the corresponding deviation values ​​ΔS1, ΔS2, and ΔS3; then, through the callback weight calculation model W for each process, obtain the callback weights w1, w2, and w3 for the physical filtration, biochemical reaction, and solid-liquid separation processes. Let i = 1, 2, 3, where i = 1 represents the physical filtration process, i = 2 represents the biochemical reaction process, and i = 3 represents the solid-liquid separation process. η i Adjust the process importance coefficients, for example, η1=0.8, η2=1.2 and η3=1, to ensure that the sum of the weights of each process is 1; S5.4: Adjustment of process parameters: Based on the deviation value ΔS and the callback weights w1, w2, and w3 of each process, calculate the adjustment range ΔP of the operating parameters for each process. i ΔP i =w i ×ΔS×k i k i Sensitivity coefficients for each process (determined experimentally, reflecting the degree of influence of parameter adjustments on the score), for example, k1=0.015, k2=0.02 and k3=0.018; then the adjustment range of the operating parameters of each process is fed back to the corresponding wastewater treatment process equipment; This embodiment requires specific explanation of the operating parameters of the physical filtration process, such as membrane filtration pressure; the operating parameters of the biochemical reaction process, such as aeration rate and carbon source dosage; and the operating parameters of the solid-liquid separation process, such as reflux ratio and sludge discharge rate.

[0023] S6: Record and store the data generated during the wastewater treatment process, update the wastewater treatment knowledge base, calculate and evaluate the wastewater quality improvement rate, optimize the model parameters using machine learning algorithms based on the evaluation anomaly results, and store the optimized model parameters in the wastewater treatment knowledge base. This includes the following steps: S6.1: Wastewater Treatment Knowledge Base Update: Store the influent water quality parameters, effluent water quality parameters, initial operating parameters of each process, scores of each process, score levels, cross-process adjustment parameters, effluent water quality parameters after control, final comprehensive water quality score, adjustment range of operating parameters of each process, and wastewater treatment water quality improvement rate in the wastewater treatment knowledge base for each control cycle. This embodiment requires specific explanation of influent water quality parameters such as influent flow rate, influent suspended solids concentration, influent turbidity, and influent COD concentration; and initial operating parameters for each process such as aeration rate, carbon source dosage, and reflux ratio.

[0024] S6.2: Calculate the wastewater treatment water quality improvement rate: Wastewater treatment water quality improvement rate ΔS fi The value is obtained by comparing the difference between the final comprehensive water quality score after control and the final comprehensive water quality score before control with the ratio of the final comprehensive water quality score before control. If ΔS fi If the value is greater than or equal to the corresponding threshold, it indicates that the intelligent collaborative control of wastewater treatment is effective. If ΔS is greater than or equal to the threshold for n consecutive control cycles (e.g., 3 or 5 cycles), it indicates that the intelligent collaborative control of wastewater treatment is effective. fi If the value is less than the corresponding threshold, it indicates an abnormal assessment. S6.3: Machine Learning Algorithm Optimization: Based on the abnormal results of the wastewater treatment water quality improvement rate assessment, a random forest regression algorithm is adopted to optimize the weight coefficients in S1, S2, and S3 with the objective of minimizing the error between the predicted scores of each process and the actual predicted scores; in order to maximize the final comprehensive water quality score S... fi To achieve the objective, optimize the weighting coefficients d1, d2, d3, and d4, and the process importance correction coefficient η. i ;Optimize the sensitivity coefficient k of each process with the goal of minimizing the number of times the operating parameters need to be adjusted. i The sensitivity coefficient reflects the degree of influence of parameter adjustment on the score. For example, k2=0.02 means that for every 1% adjustment of the aeration rate, the biochemical reaction score S2 changes by 0.02. The obtained optimized model parameters are stored in the wastewater treatment knowledge base.

[0025] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be considered as such. It is included within the scope of protection of this invention.

Claims

1. A multi-parameter intelligent collaborative control method for wastewater treatment equipment, characterized in that: include: S1: Collect monitoring parameters of the physical filtration process in wastewater treatment using data acquisition equipment, construct a mathematical model for physical filtration scoring, calculate the physical filtration treatment effect score, and classify the physical treatment score levels. S2: Through data acquisition equipment, collect monitoring parameters of the biochemical reaction process of wastewater treatment, construct a mathematical model for biochemical reaction scoring, calculate the biochemical reaction treatment effect score, and classify the biochemical reaction score level. S3: Collect monitoring parameters of the solid-liquid separation process in wastewater treatment through data acquisition equipment, construct a mathematical model for solid-liquid separation scoring, calculate the solid-liquid separation treatment effect score, and classify the solid-liquid separation score level. S4: Based on the scoring levels of physical filtration and biochemical reaction processes, construct the parameter mapping relationship between physical and biochemical processes and the parameter mapping relationship between biochemical and solid-liquid separation processes, and automatically adjust the operating parameters of subsequent processes through the control system to obtain the controlled effluent water quality parameters; S5: By monitoring the controlled effluent water quality parameters, calculate the final comprehensive water quality score, compare and analyze the deviation with the design value, establish a multi-process callback weight model to optimize the adjustment amount of each process parameter, and feed it back to the corresponding sewage treatment process equipment. S6: Record and store the data generated during the wastewater treatment process, update the wastewater treatment knowledge base, calculate and evaluate the wastewater treatment water quality improvement rate, optimize the model parameters using machine learning algorithms based on the abnormal evaluation results, and store the optimized model parameters in the wastewater treatment knowledge base.

2. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The physical filtration scoring mathematical model constructed in S1 is based on the collected monitoring parameters of the wastewater treatment physical filtration process. S1 represents the physical filtration effect score, R ss R represents the suspended solids removal rate. NTU R represents the turbidity removal rate. OIL For grease removal rate, membrane pressure difference ΔP, ΔP max A represents the maximum allowable membrane pressure difference for the membrane filtration system, and a1, a2, a3, and a4 are the corresponding weighting coefficients.

3. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The biochemical reaction scoring mathematical model constructed in S2 is based on the collected monitoring parameters of the wastewater treatment biochemical reaction process. S2 represents the biochemical reaction treatment effect score, R COD E represents the COD removal rate. nit For nitrification efficiency, E de For denitrification efficiency, R p For phosphorus removal efficiency, sludge activity SA, SA max To represent the maximum activity of the sludge, b1, b2, b3, b4, and b5 are the corresponding weighting coefficients.

4. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The solid-liquid separation scoring mathematical model S3 is constructed based on the collected monitoring parameters of the solid-liquid separation process in wastewater treatment. ΔSV 30 ΔSVI is the settling efficiency score, ΔSS is the sludge volume index performance score, and ΔSS is the sludge volume index performance score. su ΔSS represents the rate at which the concentration of suspended solids in the supernatant meets the standard. co To improve the efficiency of sludge concentration after thickening, c1, c2, c3, and c4 are the corresponding weighting coefficients.

5. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The physical-biochemical process parameter mapping relationship is constructed in S4: if the physical filtration treatment effect score S1 ≥ 0.9, the standard operating parameters of the biochemical reaction are maintained, including the aeration rate A. b Carbon source addition amount C b and hydraulic residence time tt b If 0.8 ≤ S1 < 0.9, fine-tune the operating parameters of the biochemical reaction, including adjusting the aeration rate A1. af Adjusted carbon source dosage C1 af And the adjusted hydraulic residence time tt1 af If 0.65 ≤ S1 < 0.8, further adjust the operating parameters of the biochemical reaction, including adjusting the aeration rate A2. af Adjusted carbon source dosage C2 af And the adjusted hydraulic residence time tt2 af If S1 < 0.65, enhance the operating parameters of the biochemical reaction, including adjusting the aeration rate A3. af Adjusted carbon source dosage C3 af And the adjusted hydraulic residence time tt3 af .

6. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The S4 section establishes a parameter mapping relationship for the biochemical-solid-liquid separation process: if the biochemical reaction treatment effect score S2 ≥ 0.85, the standard operating parameters for solid-liquid separation are maintained, including the reflux ratio R. b Sludge discharge volume V b and sedimentation time ct b If 0.75 ≤ S2 < 0.85, fine-tune the solid-liquid separation operating parameters, including adjusting the reflux ratio R1. af Adjusted sludge discharge volume V1 af and adjusted sedimentation time ct1 af If 0.6 ≤ S2 < 0.75, further adjust the solid-liquid separation operating parameters, including the adjusted reflux ratio R2. af Adjusted sludge discharge volume V2 af and adjusted sedimentation time ct2 af Add conventional flocculants at a dosage of 1-3 mg / L; if S2 < 0.6, enhance solid-liquid separation operating parameters, including adjusting the reflux ratio R3. af Adjusted sludge discharge volume V3 af and adjusted sedimentation time ct3 af Add a strong flocculant at a dosage of 5-10 mg / L.

7. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The final comprehensive water quality score is calculated in S5 by monitoring effluent water quality parameters, including effluent COD concentration. out effluent ammonia nitrogen concentration (NH3) out The final comprehensive water quality score S is calculated based on the effluent total phosphorus concentration TP_out and the effluent suspended solids concentration SS_out. fi S fi =d1×COD sc +d2×NH3 sc +d3×TP sc +d4×SS sc d1, d2, d3, and d4 are the corresponding weights, and the COD compliance score is calculated based on the COD score. sc Ammonia nitrogen compliance score (NH3) sc Total phosphorus (TP) score sc Suspended solids compliance score SS sc .

8. The multi-parameter intelligent collaborative control method for sewage treatment equipment according to claim 1, characterized in that: The analytical bias in S5: Calculate the final comprehensive water quality score S. fi The absolute difference from the design value is used to obtain the deviation value ΔS; then the callback strategy is determined: if ΔS≤0.05, the adjustment range is ≤5%; if 0.05<ΔS≤0.15, the adjustment range is 0.05 to 0.15; if ΔS>0.15, the adjustment range is >0.15 and the equipment operating status needs to be checked simultaneously.

9. A multi-parameter intelligent collaborative control method for wastewater treatment equipment according to claim 1, characterized in that: In S5, a multi-process callback weight model is established to optimize the adjustment amount of parameters for each process: A multi-process callback weight model is established: First, the absolute differences between the scores S1, S2, and S3 of each process and their corresponding design values ​​are calculated to obtain the corresponding deviation values ​​ΔS1, ΔS2, and ΔS3; then, the callback weights w1, w2, and w3 of the physical filtration, biochemical reaction, and solid-liquid separation processes are obtained through the callback weight calculation model W. Let i = 1, 2, 3, where i = 1 represents the physical filtration process, i = 2 represents the biochemical reaction process, and i = 3 represents the solid-liquid separation process. η i This is a correction factor for process importance. Adjustment of process parameters: Based on the deviation value ΔS and the callback weights w1, w2, and w3 of each process, calculate the adjustment range ΔP of the operating parameters for each process. i ΔP i =w i ×ΔS×k i k i The sensitivity coefficients for each process are then used; the adjustment range of the operating parameters for each process is then fed back to the corresponding wastewater treatment process.

Images