Sewage treatment control model parameter calibration method

Abstract

The invention relates to the technical field of sewage treatment, in particular to a sewage treatment control model parameter calibration method which comprises the following steps: monitoring effluent quality data corresponding to a sewage treatment system in real time to form corresponding effluent quality monitoring data; according to the outlet water quality monitoring data monitored at the current moment, whether the corresponding outlet water quality monitoring data at the current moment meets a preset water quality threshold value or not is judged based on a preset outlet water quality judgment strategy; when the judgment result is that the effluent quality of the sewage treatment system at the current moment does not reach the standard, calling a process control scheme and a sewage treatment mechanism model corresponding to the sewage treatment system at the current moment, and correcting a strategy based on a preset mechanism model; and correcting the model parameters of the sewage treatment mechanism model corresponding to the sewage treatment system at the current moment, and taking the corrected sewage treatment mechanism model as the corresponding sewage treatment mechanism model at the next moment.

Description

Technical Field

[0001] The invention relates to the technical field of sewage treatment, and in particular to a sewage treatment control model parameter calibration method. Background Art

[0002] Wastewater treatment plays a vital role in global water resource management. With increasingly stringent environmental regulations and the public's increasing demand for water quality, wastewater treatment plants are faced with the challenge of ensuring that effluent quality remains stable and up to standard.

[0003] Traditionally, sewage treatment processes rely on fixed operating parameters and empirical rules to control treatment effects, but this approach is difficult to adapt to the dynamic changes in sewage composition, especially when faced with seasonal fluctuations, emergencies or complex pollutants, which can easily lead to decreased treatment efficiency and unstable effluent quality.

[0004] With the continuous advancement of science and technology, intelligent control systems based on mechanism models have gradually become an effective means to improve sewage treatment efficiency. Although the existing sewage treatment system uses intelligent control based on mechanism models to control sewage treatment, there are still some problems:

[0005] Most of the mechanism models used in existing sewage treatment systems require regular parameter calibration to maintain their prediction accuracy and control effects. However, in actual operations, due to the high variability and complexity of sewage components, existing mechanism models are difficult to fully and accurately simulate real-world conditions.

[0006] Therefore, in order to ensure the effectiveness of the model and the reliability of the treatment results, technicians usually need to manually adjust the model parameters. Whenever the influent water quality changes significantly or encounters atypical working conditions, experienced engineers need to intervene and recalibrate the model parameters through trial and error or other methods. The manual adjustment process is time-consuming, and there is a delay between discovering the problem and taking action, which may result in substandard effluent quality for a period of time. Effective parameter adjustment requires not only deep professional knowledge, but also a deep understanding of the specific sewage treatment facilities, which sets a high threshold for operators and increases training costs.

[0007] Based on this, there is an urgent need for a sewage treatment control model parameter calibration method to realize abnormal monitoring of effluent water quality during the operation of the sewage treatment system, automatically adjust the model parameters, quickly respond to various changes, reduce the need for manual intervention, and achieve rapid and accurate response of the sewage treatment system. Summary of the invention

[0008] One of the purposes of the present invention is to provide a method for calibrating parameters of a sewage treatment control model, so as to realize monitoring of abnormal effluent water quality during the operation of the sewage treatment system, automatically adjust the model parameters, quickly respond to various changes, reduce the need for manual intervention, and realize rapid and accurate response of the sewage treatment system.

[0009] In order to achieve the above object, a method for calibrating parameters of a sewage treatment control model is provided, comprising the following steps:

[0010] S1. Real-time monitoring of the effluent water quality data corresponding to the sewage treatment system to form corresponding effluent water quality monitoring data;

[0011] S2. According to the effluent water quality monitoring data monitored at the current moment, based on the preset effluent water quality judgment strategy, it is judged whether the effluent water quality monitoring data corresponding to the current moment meets the preset water quality threshold. If so, it is judged that the effluent water quality of the sewage treatment system at the current moment meets the standard. Otherwise, the effluent water quality of the sewage treatment system at the current moment does not meet the standard;

[0012] S3. When it is judged that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the process control scheme and sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are retrieved, and based on the preset mechanism model correction strategy, the model parameters of the sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are corrected, and the corrected sewage treatment mechanism model is used as the sewage treatment mechanism model corresponding to the next moment.

[0013] Technical principles and effects of this solution: In this solution, the effluent water quality data corresponding to the sewage treatment system is monitored in real time to form corresponding effluent water quality monitoring data. This step ensures a comprehensive grasp of the system's operating status and provides an accurate basis for subsequent judgments. According to the effluent water quality monitoring data monitored at the current moment, based on the preset effluent water quality judgment strategy, it is judged whether the effluent water quality monitoring data corresponding to the current moment is greater than the preset water quality threshold. If so, it is judged that the effluent water quality of the sewage treatment system at the current moment meets the standard; otherwise, it is judged that the effluent water quality of the sewage treatment system at the current moment does not meet the standard. This step ensures strict monitoring of the effluent water quality and timely detection of problems by setting clear water quality thresholds.

[0014] When the judgment result is that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the process control scheme and sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are retrieved, and based on the preset mechanism model correction strategy, the model parameters of the sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are corrected. The corrected sewage treatment mechanism model is used as the sewage treatment mechanism model corresponding to the next moment to ensure that the water quality can be controlled more accurately in the next operation. By dynamically adjusting the model parameters, the system can respond quickly and correct deviations to maintain the stability and consistency of the effluent water quality.

[0015] In this solution, real-time monitoring and instant feedback mechanisms ensure that the system can detect and correct water quality problems in the first place, avoid the risk of long-term excessive discharge, and improve the stability and reliability of effluent water quality. Based on the preset mechanism model correction strategy, the system can dynamically adjust the model parameters according to the actual operation situation, enhance the adaptability to different working conditions and emergencies, and reduce the risk of treatment failure caused by changes in the external environment. By precisely controlling the model parameters, the system can use resources more efficiently, reduce unnecessary consumption, reduce operating costs, and improve treatment efficiency. That is, during the operation of the sewage treatment system, the system can monitor the abnormalities of the effluent water quality, automatically adjust the model parameters, quickly respond to various changes, reduce the need for manual intervention, and achieve rapid and accurate response of the sewage treatment system.

[0016] Furthermore, the preset outlet water quality judgment strategy is:

[0017] S20, after collecting the effluent water quality monitoring data corresponding to the current moment, retrieve the historical effluent water quality monitoring data corresponding to the previous moment and the previous moment from the historical database, as well as the historical influent data and effluent water quality simulation data corresponding to the effluent water quality monitoring data at the current moment and the historical effluent water quality monitoring data; the effluent water quality simulation data is the output data corresponding to the influent data at the corresponding moment and the process control scheme after being input as input data into the sewage treatment mechanism model at the corresponding moment;

[0018] S21. Calculate the prediction error value of the sewage treatment mechanism model corresponding to the current moment based on the effluent water quality monitoring data at the previous moment and the moment before that, and the effluent water quality simulation data corresponding to each moment, and determine whether the corresponding prediction error value is greater than the preset error threshold. If so, determine that the effluent water quality monitoring data corresponding to the current moment meets the water quality threshold, otherwise, it does not meet the threshold.

[0019] Beneficial effects: In this scheme, by introducing historical data (data from the last moment and the moment before that) and effluent water quality simulation data, not only real-time monitoring data is considered, but also model prediction results are combined to improve the comprehensiveness and accuracy of effluent water quality judgment. The prediction error value is calculated and the preset error threshold is set to ensure the scientificity and rationality of the judgment standard and avoid the misjudgment that may be caused by relying solely on real-time data.

[0020] Comprehensively utilizing data from multiple time points for analysis reduces misjudgments caused by abnormal or fluctuating data at a certain moment, and enhances the stability and reliability of the system. Dynamically adjusting the preset error threshold can be optimized according to actual conditions, further improving the adaptability and flexibility of the system.

[0021] Furthermore, the mechanism model correction strategy is:

[0022] S30, when the result of the judgment is that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the adjustment sensitivity of each model parameter corresponding to the sewage treatment mechanism model at the current moment is identified, and the adjustment sensitivity is sorted in descending order to form a sensitivity sorting table;

[0023] S31, selecting the model parameter with the highest adjustment sensitivity according to the sensitivity ranking table;

[0024] S32. After selecting the corresponding intermediate control parameter, the model parameter is corrected and adjusted based on the preset adjustment amount. After the correction is completed, the sewage treatment mechanism model corresponding to the current moment is updated, and the historical water inlet data corresponding to the effluent monitoring data corresponding to the current moment and the process control scheme corresponding to the sewage treatment system at the current moment are input as input data to the updated sewage treatment mechanism model corresponding to the current moment, and the corresponding effluent water quality re-simulation data is output;

[0025] S33, judging whether the simulation error between the effluent water quality re-simulation data and the effluent water quality monitoring data is less than the preset simulation error, if so, the corresponding updated sewage treatment mechanism model at the current moment is a feasible model;

[0026] If not, select the next model parameter with the highest adjustment sensitivity and re-execute S34 until the effluent water quality re-simulation data and the effluent water quality monitoring data are within the preset simulation error. At this time, it is judged that the updated sewage treatment mechanism model corresponding to the current moment is a feasible model.

[0027] Beneficial effects: In this solution, when the judgment result is that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the adjustment sensitivity of each model parameter corresponding to the sewage treatment mechanism model at the current moment is identified. The adjustment sensitivity is sorted from large to small to form a sensitivity ranking table. This step ensures that the parameters that have the greatest impact on the effluent water quality are adjusted first, thereby achieving efficient optimization. According to the sensitivity ranking table, the model parameters with the highest adjustment sensitivity are selected. This method ensures that each adjustment can bring significant improvements and avoids unnecessary parameter adjustments.

[0028] After the correction is completed, the sewage treatment mechanism model corresponding to the current moment is updated, and the historical water inlet data corresponding to the effluent monitoring data corresponding to the current moment, and the process control plan corresponding to the current moment of the sewage treatment system are re-input as input data into the updated sewage treatment mechanism model corresponding to the current moment, and the corresponding effluent water quality re-simulation data is output.

[0029] This step ensures that the model can be verified immediately after each adjustment and the adjustment effect can be fed back in time. That is, by identifying and prioritizing the model parameters that have the greatest impact on the effluent water quality, the number of unnecessary adjustments is reduced and the optimization efficiency is improved. Verification is performed immediately after each adjustment to ensure that each adjustment can bring significant improvements and avoid system instability that may be caused by adjusting too many parameters at one time. After each adjustment, a strict error evaluation is performed, and the adjustment will only be stopped when the simulation error meets the requirements, ensuring the effectiveness and reliability of the final model and enhancing the stability and consistency of the system. By setting a preset simulation error, the overfitting problem caused by excessive adjustment is prevented, and the long-term stable operation of the system is maintained.

[0030] Furthermore, the calculation formula corresponding to the prediction error value of the sewage treatment mechanism model corresponding to the current moment calculated in S21 is:

[0031]

[0032] Where W is the prediction error value, y t is the effluent water quality monitoring data at the current time t, is the effluent water quality simulation data at the current time t, w1, w2, w3 are the corresponding dynamically changing weight values, the greater the absolute value of the difference between the effluent water quality monitoring data and the effluent water quality simulation data at each time, the greater the corresponding weight value, ∝ is the corresponding weighting coefficient, E t It is the variable value affected by the external environmental factors corresponding to the current time t.

[0033] Beneficial effects: In this solution, by simultaneously considering the data at the current moment, the previous moment, and the moment before that, the formula can more comprehensively evaluate the prediction accuracy of the model, avoiding the one-sidedness that may be caused by the error evaluation at a single time point. The weight is dynamically adjusted according to the absolute value of the error at each moment, ensuring that key errors (i.e., larger errors) are focused on, and improving the adaptability and flexibility of the model. Larger errors are given higher weights, allowing the system to prioritize those issues that have the greatest impact on the effluent water quality, thereby correcting deviations more quickly. By introducing historical data and assigning appropriate weights, the impact of abnormal or fluctuating data at a single time point is reduced, and the stability of the overall prediction is improved. Each adjusted model can be verified immediately, ensuring that the model is always in the best state, improving the prediction accuracy and processing effect.

[0034] Furthermore, the process control scheme includes multiple intermediate control parameters corresponding to the sewage treatment system, and the intermediate control parameters include gas volume parameters, DO values, oxygen demand parameters, internal reflux ratio parameters, external reflux ratio parameters, sludge discharge parameters and dosing parameters corresponding to the sewage treatment system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a method for calibrating parameters of a sewage treatment control model in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0036] The following is further described in detail through specific implementation methods:

[0037] Embodiment 1

[0038] The parameter calibration method of sewage treatment control model is basically as follows Figure 1 As shown, the following steps are included:

[0039] S1. Real-time monitoring of the effluent water quality data corresponding to the sewage treatment system to form corresponding effluent water quality monitoring data;

[0040] S2. According to the effluent water quality monitoring data monitored at the current moment, based on the preset effluent water quality judgment strategy, it is judged whether the effluent water quality monitoring data corresponding to the current moment meets the preset water quality threshold. If so, it is judged that the effluent water quality of the sewage treatment system at the current moment meets the standard. Otherwise, the effluent water quality of the sewage treatment system at the current moment does not meet the standard;

[0041] The preset outlet water quality judgment strategy is:

[0042] S20. After collecting the effluent water quality monitoring data corresponding to the current moment, retrieve the historical effluent water quality monitoring data corresponding to the previous moment and the moment before that from the historical database, as well as the effluent water quality monitoring data at the current moment and the historical inlet data and effluent water quality simulation data corresponding to the historical effluent water quality monitoring data; the effluent water quality simulation data is the output data corresponding to the inlet data and the process control scheme corresponding to the sewage treatment system at the corresponding moment after being input as input data into the sewage treatment mechanism model at the corresponding moment; in this embodiment, the process control scheme includes multiple intermediate control parameters corresponding to the sewage treatment system, and the intermediate control parameters include the gas volume parameter, DO value, oxygen demand parameter, internal reflux ratio parameter, external reflux ratio parameter, sludge discharge parameter and dosage parameter corresponding to the sewage treatment system. In this embodiment, before inputting into the sewage treatment mechanism model, the influent data needs to be cleaned to ensure that the influent monitoring data enters the model in the format required by the algorithm. This step includes the parameters of the influent component distribution ratio (the percentage of each component). The sewage treatment plant with relatively complete influent online monitoring mainly monitors: COD / TN / TP / SS / NH4. The model needs to clean these data before use, and the ratio needs to be dynamically calibrated.

[0043] S21. Calculate the prediction error value of the sewage treatment mechanism model corresponding to the current moment based on the effluent water quality monitoring data at the previous moment and the moment before that, and the effluent water quality simulation data corresponding to each moment, and determine whether the corresponding prediction error value is greater than the preset error threshold. If so, determine that the effluent water quality monitoring data corresponding to the current moment meets the water quality threshold, otherwise, it does not meet the threshold.

[0044] The calculation formula corresponding to the prediction error value of the sewage treatment mechanism model corresponding to the current moment calculated in S21 is:

[0045]

[0046] Where W is the prediction error value, y t is the effluent water quality monitoring data at the current time t, is the effluent water quality simulation data at the current time t, w1, w2, w3 are the corresponding dynamically changing weight values, the greater the absolute value of the difference between the effluent water quality monitoring data and the effluent water quality simulation data at each time, the greater the corresponding weight value, ∝ is the corresponding weighting coefficient, E t It is the variable value corresponding to the variable affected by the external environmental factors at the current time t.

[0047] S3. When the judgment result is that the effluent water quality of the sewage treatment system at the current moment is not up to standard, the process control scheme and sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are retrieved, and based on the preset mechanism model correction strategy, the model parameters of the sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are corrected, and the corrected sewage treatment mechanism model is used as the sewage treatment mechanism model corresponding to the next moment. In this embodiment, the corresponding model parameters include the kinetic parameters and stoichiometric parameters of the mechanism model itself. These parameters change with the ambient temperature, season, and microbial growth, and need to be calibrated.

[0048] The mechanism model correction strategy is:

[0049] S30. When the judgment result is that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the adjustment sensitivity of each model parameter corresponding to the sewage treatment mechanism model at the current moment is identified, and the adjustment sensitivity is sorted in descending order to form a sensitivity sorting table; in this embodiment, the adjustment sensitivity corresponding to each model parameter corresponding to the sewage treatment mechanism model is stored in the historical database. During specific identification, after the corresponding model parameter is identified, the adjustment sensitivity of the corresponding model parameter can be retrieved from the historical database, and then the corresponding sorting is performed.

[0050] S31, selecting the model parameter with the highest adjustment sensitivity according to the sensitivity ranking table;

[0051] S32. After selecting the corresponding intermediate control parameter, the model parameter is corrected and adjusted based on the preset adjustment amount. After the correction is completed, the sewage treatment mechanism model corresponding to the current moment is updated, and the historical water inlet data corresponding to the effluent monitoring data corresponding to the current moment and the process control scheme corresponding to the sewage treatment system at the current moment are input as input data to the updated sewage treatment mechanism model corresponding to the current moment, and the corresponding effluent water quality re-simulation data is output;

[0052] S33, judging whether the simulation error between the effluent water quality re-simulation data and the effluent water quality monitoring data is less than the preset simulation error, if so, the corresponding updated sewage treatment mechanism model at the current moment is a feasible model;

[0053] If not, select the next model parameter with the highest adjustment sensitivity, and re-execute S34 until the effluent water quality re-simulation data and the effluent water quality monitoring data are within the preset simulation error, and then judge that the updated sewage treatment mechanism model corresponding to the current moment is a feasible model. In this embodiment, for example, the corresponding model parameters include parameters A, B, and C, wherein the magnitude relationship of the adjustment sensitivity corresponding to each parameter is respectively that parameter C is the largest, parameter B is the smallest, and parameter A is in the middle. When the corresponding model parameters are selected to parameters A, B, and C, the parameter C with the largest adjustment sensitivity will be selected first, and then based on the preset adjustment amount such as adjusting 10%, the previously corrected parameters, as well as the currently corrected parameter C, and other parameters that have not been corrected, including parameters A and C, are used to complete the correction of the corresponding sewage treatment mechanism model to form a corrected sewage treatment mechanism model, and then the corrected sewage treatment mechanism model is used to perform another simulation judgment. If it is not a feasible model, parameter A will continue to be selected, and the adjustment of the above-mentioned parameter C will be performed again until the corresponding corrected sewage treatment mechanism model is a feasible model after a certain parameter adjustment is completed.

[0054] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme will not be described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for the ordinary technicians in the relevant field to implement this application. It should be pointed out that for the technicians in this field, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to explain the content of the claims.

Claims

1. A method for calibrating parameters of a sewage treatment control model, characterized in that: The following steps are involved: S1. Real-time monitoring of the effluent water quality data corresponding to the sewage treatment system to form corresponding effluent water quality monitoring data; S2. According to the effluent water quality monitoring data monitored at the current moment, based on the preset effluent water quality judgment strategy, it is judged whether the effluent water quality monitoring data corresponding to the current moment meets the preset water quality threshold. If so, it is judged that the effluent water quality of the sewage treatment system at the current moment meets the standard. Otherwise, the effluent water quality of the sewage treatment system at the current moment does not meet the standard; S3. When it is judged that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the process control scheme and sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are retrieved, and based on the preset mechanism model correction strategy, the model parameters of the sewage treatment mechanism model corresponding to the sewage treatment system at the current moment are corrected, and the corrected sewage treatment mechanism model is used as the sewage treatment mechanism model corresponding to the next moment.

2. The method for calibrating parameters of a sewage treatment control model according to claim 1, characterized in that: The preset outlet water quality judgment strategy is: S20, after collecting the effluent water quality monitoring data corresponding to the current moment, retrieve the historical effluent water quality monitoring data corresponding to the previous moment and the previous moment from the historical database, as well as the historical influent data and effluent water quality simulation data corresponding to the effluent water quality monitoring data at the current moment and the historical effluent water quality monitoring data; the effluent water quality simulation data is the output data corresponding to the influent data at the corresponding moment and the process control scheme after being input as input data into the sewage treatment mechanism model at the corresponding moment; S21. Calculate the prediction error value of the sewage treatment mechanism model corresponding to the current moment based on the effluent water quality monitoring data at the previous moment and the moment before that, and the effluent water quality simulation data corresponding to each moment, and determine whether the corresponding prediction error value is greater than the preset error threshold. If so, determine that the effluent water quality monitoring data corresponding to the current moment meets the water quality threshold, otherwise, it does not meet the threshold.

3. The method for calibrating parameters of a sewage treatment control model according to claim 2, characterized in that: The mechanism model correction strategy is: S30, when the result of the judgment is that the effluent water quality of the sewage treatment system at the current moment does not meet the standard, the adjustment sensitivity of each model parameter corresponding to the sewage treatment mechanism model at the current moment is identified, and the adjustment sensitivity is sorted in descending order to form a sensitivity sorting table; S31, selecting the model parameter with the highest adjustment sensitivity according to the sensitivity ranking table; S32. After selecting the corresponding intermediate control parameter, the model parameter is corrected and adjusted based on the preset adjustment amount. After the correction is completed, the sewage treatment mechanism model corresponding to the current moment is updated, and the historical water inlet data corresponding to the effluent monitoring data corresponding to the current moment and the process control scheme corresponding to the sewage treatment system at the current moment are input as input data to the updated sewage treatment mechanism model corresponding to the current moment, and the corresponding effluent water quality re-simulation data is output; S33, judging whether the simulation error between the effluent water quality re-simulation data and the effluent water quality monitoring data is less than the preset simulation error, if so, the corresponding updated sewage treatment mechanism model at the current moment is a feasible model; If not, select the next model parameter with the highest adjustment sensitivity and re-execute S34 until the effluent water quality re-simulation data and the effluent water quality monitoring data are within the preset simulation error. At this time, it is judged that the updated sewage treatment mechanism model corresponding to the current moment is a feasible model.

4. The method for calibrating parameters of a sewage treatment control model according to claim 3, characterized in that: The calculation formula corresponding to the prediction error value of the sewage treatment mechanism model corresponding to the current moment calculated in S21 is: Where W is the prediction error value, y t is the effluent water quality monitoring data at the current time t, is the effluent water quality simulation data at the current time t, w1, w2, w3 are the corresponding dynamically changing weight values, the greater the absolute value of the difference between the effluent water quality monitoring data and the effluent water quality simulation data at each time, the greater the corresponding weight value, ∝ is the corresponding weighting coefficient, E t It is the variable value affected by the external environmental factors corresponding to the current time t.

5. The method for calibrating parameters of a sewage treatment control model according to claim 4, characterized in that: The process control scheme includes multiple intermediate control parameters corresponding to the sewage treatment system, and the intermediate control parameters include gas volume parameters, DO values, oxygen demand parameters, internal reflux ratio parameters, external reflux ratio parameters, sludge discharge parameters and dosing parameters corresponding to the sewage treatment system.

Images