Sewage process parameter regulation and control method and system based on artificial intelligence

Abstract

The invention discloses a sewage process parameter regulation and control method and system based on artificial intelligence, and relates to the technical field of data analysis, and the method comprises the steps: analyzing the interaction relationship between basic parameters and the interaction relationship between the basic parameters and evaluation parameters; the relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters are accurately analyzed, and a reliable basis is provided for subsequent multi-objective optimization and regulation. And the weight of each evaluation parameter is set according to the action relation of the basic parameters on the evaluation parameters and the fluctuation condition of the evaluation parameters. The inertia weight in the MOPSO algorithm is set, and the optimal solution of the multi-target optimization model is solved through the MOPSO algorithm, so that the local and global search capabilities are balanced, and the quality of the optimal solution is improved. Cooperative regulation and control are carried out on sewage process parameters based on an adaptive control strategy and an optimal solution of a multi-objective optimization model, and the process parameter regulation and control effect is comprehensively and effectively improved in combination with adaptive control and multi-objective optimization.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a sewage process parameter control method and system based on artificial intelligence. Background Art

[0002] With the rapid development of industrialization and urbanization, sewage treatment faces increasingly complex challenges. Traditional sewage process parameter control relies on manual experience and fixed process parameters, making it difficult to adapt to water quality fluctuations and changes in operating conditions. Therefore, an artificial intelligence-based sewage process parameter control solution has emerged. This solution uses advanced algorithms such as neural networks and machine learning to conduct real-time analysis of large amounts of data from the sewage treatment process, accurately predict water quality changes, and dynamically adjust key parameters such as DO and MLSS. By building a closed-loop system of "perception-analysis-decision-execution", sewage treatment can be transformed from "water management based on experience" to "water management based on algorithms", effectively improving treatment efficiency, reducing energy consumption, ensuring stable and standard effluent water quality, and promoting the sewage treatment industry to develop in an intelligent and efficient direction.

[0003] In the existing technology, because there are multiple objectives in sewage treatment, it is difficult to ensure the balance between multiple objectives, resulting in poor accuracy and adaptability of sewage process parameter control, which cannot meet the changing sewage treatment conditions and the sewage process parameter control effect is low.

[0004] Therefore, how to improve the accuracy and adaptability of sewage process parameter regulation is a technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of poor accuracy and adaptability of sewage process parameter control in the prior art, and to propose a sewage process parameter control method based on artificial intelligence, which includes: Collect all sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, including basic parameters and evaluation parameters, and analyze the relationship between basic parameters and the relationship between basic parameters and evaluation parameters; Calculate the fluctuation of basic parameters and evaluation parameters, set the weight of each evaluation parameter based on the relationship between basic parameters and evaluation parameters, and define the stability level of the processing condition according to the fluctuation of basic parameters; By processing the stability level of the working condition, the weights of the evaluation parameters are dynamically adjusted, a multi-objective optimization model is constructed, the inertia weight in the MOPSO algorithm is set, and the optimal solution of the multi-objective optimization model is solved by the MOPSO algorithm; An adaptive control strategy is set, and the sewage process parameters are coordinated and regulated based on the optimal solution of the adaptive control strategy and the multi-objective optimization model.

[0006] In some embodiments of the present application, the interaction relationships between basic parameters and the interaction relationships between basic parameters and evaluation parameters are analyzed, including: The interaction relationships between different basic parameters are analyzed through multiple regression analysis, and significant interaction relationships are screened based on the P-value; According to the sewage treatment mechanism model, a hypothetical causal path between the basic parameters and the evaluation parameters is given, and a theoretical causal path diagram is constructed. The nodes in the theoretical causal path diagram are basic parameters or evaluation parameters, and the edges or paths represent the relationships between basic parameters or the relationships between basic parameters and evaluation parameters; The path coefficient of each path is calculated and marked at the corresponding position in the theoretical causal path diagram. The direct effect interaction relationship and the indirect effect interaction relationship are divided according to the proximity relationship between the nodes on the theoretical causal path diagram. Based on the path coefficient, the direct effect interaction relationship and the indirect effect interaction relationship, the interaction relationship between the basic parameters and the evaluation parameters is determined.

[0007] In some embodiments of the present application, the fluctuations of the basic parameters and the evaluation parameters are statistically analyzed, including: The standard deviations and averages of the basic parameters and the evaluation parameters are statistically obtained, and the coefficient of variation of the basic parameters and the evaluation parameters is calculated according to the standard deviation and the average. The fluctuations of the basic parameters and the evaluation parameters are described by the coefficient of variation.

[0008] In some embodiments of the present application, the weight of each evaluation parameter is set in combination with the interaction relationship between the basic parameters and the evaluation parameter, including: The interaction relationships between the basic parameters and the evaluation parameter are divided into multiple groups with the evaluation parameter as the unit, and the multiple path coefficients in the theoretical causal path diagram corresponding to the interaction relationships between the basic parameters and the evaluation parameter are integrated to obtain the action intensity; For the same evaluation parameter, the weight of each evaluation parameter is determined according to the coefficient of variation and the action intensity.

[0009] In some embodiments of the present application, the weight of the evaluation parameter is dynamically adjusted through the stable level of the treatment condition, including: It is judged whether the current sewage treatment condition belongs to a stable state through the stable level of the treatment condition; If the current sewage treatment condition belongs to a stable state, the weight of the evaluation parameter does not need to be adjusted; Otherwise, the weight of the evaluation parameter is adjusted according to the interaction relationship between the basic parameters and the evaluation parameter.

[0010] In some embodiments of the present application, a multi-objective optimization model is constructed, including: Taking each evaluation parameter as a unit, construct the objective function of each evaluation parameter based on the interaction relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters, and synthesize the objective functions of all evaluation parameters to generate a comprehensive objective function model; Collect multiple types of constraint factors required for the sewage treatment process, and determine the constraint conditions of the parameters in the multi-objective optimization model according to the multiple types of constraint factors.

[0011] In some embodiments of the present application, set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm, including, Based on the interaction relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters, perform local sensitivity analysis and global sensitivity analysis respectively, and determine the sensitive indicators by combining the results of the two sensitivity analyses; Analyze the correlation between the evaluation parameters to determine the conflict indicators of the evaluation parameters, determine the inertia weight according to the sensitive indicators and the conflict indicators, thereby implementing the MOPSO algorithm and calculating the optimal solution of the multi-objective optimization model.

[0012] In some embodiments of the present application, based on the adaptive control strategy and the optimal solution of the multi-objective optimization model, co-regulate the sewage process parameters, including, Output the first control target interval according to the adaptive control strategy, and output the second control target interval according to the optimal solution of the multi-objective optimization model; If there is an intersection between the first control target interval and the second control target interval, then regulate the sewage process parameters for the intersection of the control target intervals; Otherwise, regulate the sewage process parameters according to the deviation between the first control target interval and the second control target interval.

[0013] Correspondingly, the present application also provides a sewage process parameter regulation system based on artificial intelligence, including, The first module is used to collect all the sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, the sewage process parameters include basic parameters and evaluation parameters, and analyze the interaction relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters; The second module is used to count the fluctuation conditions of the basic parameters and the evaluation parameters, and set the weight of each evaluation parameter in combination with the relationship between the basic parameters and the evaluation parameters, and define the stability level of the treatment working condition according to the fluctuation conditions of the basic parameters; The third module is used to dynamically adjust the weight of the evaluation parameter through the stability level of the treatment working condition, construct a multi-objective optimization model, set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm; The fourth module is used to set an adaptive control strategy and coordinately regulate the sewage process parameters based on the adaptive control strategy and the optimal solution of the multi-objective optimization model.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Analyze the interaction relationships among the basic parameters and the relationships between the basic parameters and the evaluation parameters, accurately analyze the relationships among the basic parameters and the relationships between the basic parameters and the evaluation parameters, and provide a reliable basis for subsequent multi-objective optimization and regulation. Set the weight of each evaluation parameter by combining the relationship between the basic parameter and the evaluation parameter and the fluctuation of the evaluation parameter, improve the adaptability and stability of multi-objective optimization, and balance the requirements of multiple objectives as much as possible. Dynamically adjust the weight of the evaluation parameter by processing the working condition stability level, monitor the sewage treatment working condition, and judge whether the weight of the multi-objective parameter needs to be adjusted, so as to adjust in time and ensure timeliness.

[0015] 2. Set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm, balance the local and global search capabilities, and improve the quality of the optimal solution. Coordinately regulate the sewage process parameters based on the adaptive control strategy and the optimal solution of the multi-objective optimization model, combine adaptive control and multi-objective optimization, comprehensively and effectively improve the regulation effect of the process parameters, improve the accuracy and adaptability of the sewage process parameter regulation, and ensure the balance between multiple objectives of sewage treatment and the sewage treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flow chart of a method for regulating sewage process parameters based on artificial intelligence proposed by the present invention; Figure 2 is a schematic structural diagram of a system for regulating sewage process parameters based on artificial intelligence proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0018] Refer to Figure 1 , a method for regulating sewage process parameters based on artificial intelligence includes the following steps: Step S101, collect all the sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, the sewage process parameters include basic parameters and evaluation parameters, and analyze the interaction relationships among the basic parameters and the relationships between the basic parameters and the evaluation parameters.

[0019] In this embodiment, the basic parameters and evaluation parameters include the following: Physical parameters: flow rate (Q), temperature (T), dissolved oxygen (DO), mixed liquor suspended solids (MLSS).

[0020] Chemical parameters: chemical oxygen demand (COD), ammonia nitrogen (NH3-N), total phosphorus (TP), pH value.

[0021] Operating parameters: aeration rate (A), reflux ratio (R), sludge retention time (SRT), hydraulic retention time (HRT).

[0022] Evaluation parameters: Water quality targets: effluent COD, effluent ammonia nitrogen, effluent TP.

[0023] Energy consumption targets: aeration energy consumption, pumping energy consumption.

[0024] Cost targets: chemical cost, sludge disposal cost.

[0025] In this embodiment, there may be mutual influences among the basic parameters, and the basic parameters will affect the evaluation parameters. It is necessary to consider two kinds of influence relationships to provide a basis for the follow-up.

[0026] In some embodiments of the present application, analyze the interaction relationships between the basic parameters and the interaction relationships of the basic parameters with respect to the evaluation parameters, including, Analyze the interaction relationships between different basic parameters through multiple regression analysis, and screen out significant interaction relationships based on the P value; Give the hypothesized causal paths between the basic parameters and the evaluation parameters according to the sewage treatment mechanism model, construct a theoretical causal path diagram, where the nodes in the theoretical causal path diagram are basic parameters or evaluation parameters, and the edges or paths represent the relationships between basic parameters or the relationships between basic parameters and evaluation parameters; Calculate the path coefficient of each path and mark it at the corresponding position of the theoretical causal path diagram. Divide the direct effect relationship and the indirect effect relationship according to the proximity relationship between the nodes on the theoretical causal path diagram. Determine the relationship of the basic parameters with respect to the evaluation parameters based on the path coefficient, direct effect relationship and indirect effect relationship.

[0027] In this embodiment, analyze the interaction relationships between different basic parameters through multiple regression analysis, and distinguish whether it is significant through a threshold. Analyze different basic parameters as independent variables and dependent variables respectively. Based on the sewage treatment mechanism, propose all possible hypothesized causal paths.

[0028] For example, DO → microbial activity → effluent COD (Path 1); MLSS → sludge load → effluent COD (Path 2); Aeration volume → DO → Microbial activity → Effluent COD (Path 3, indirect).

[0029] Theoretical causal path diagram: Nodes: DO, MLSS, Aeration volume, Microbial activity, Sludge loading, Effluent COD.

[0030] Edges / paths: DO → Microbial activity (Path coefficient 0.6); Microbial activity → Effluent COD (Path coefficient -0.8); MLSS → Sludge loading (Path coefficient -0.4); Sludge loading → Effluent COD (Path coefficient 0.5); Aeration volume → DO (Path coefficient 0.3).

[0031] The path coefficient is the degree of influence between two nodes. The direct effect relationship and the indirect effect relationship are divided according to the proximity relationship between the nodes on the theoretical causal path diagram. The adjacent nodes (between the basic parameter and the evaluation parameter) are in a direct effect relationship, otherwise it is an indirect effect relationship. For example: Direct effect: DO → Microbial activity → Effluent COD (Path 1); MLSS → Sludge loading → Effluent COD (Path 2); Indirect effect: Aeration volume → DO → Microbial activity → Effluent COD (Path 3).

[0032] Step S102, statistically analyze the fluctuations of the basic parameters and the evaluation parameters, and set the weight of each evaluation parameter in combination with the action relationship of the basic parameter on the evaluation parameter, and define the stability level of the treatment condition according to the fluctuation of the basic parameter.

[0033] In this embodiment, the fluctuations of the basic parameters and the evaluation parameters will affect the weights of the subsequent multi-objective optimization and the stability of the working condition, so these contents are considered for setting and monitoring.

[0034] [[ID=4i]]In some embodiments of the present application, statistically analyzing the fluctuations of the basic parameters and the evaluation parameters includes Calculating the standard deviation and the average value of the basic parameters and the evaluation parameters, and calculating the coefficient of variation of the basic parameters and the evaluation parameters according to the standard deviation and the average value, and describing the fluctuations of the basic parameters and the evaluation parameters through the coefficient of variation.

[0035] In this embodiment, the coefficient of variation of each parameter is calculated by the ratio of the standard deviation to the average value to describe the fluctuation of the parameter. [[ID=Zi]]

[0036] In some embodiments of the present application, the weight of each evaluation parameter is set in combination with the relationship between the basic parameters and the evaluation parameter, including Dividing the relationship between multiple groups of basic parameters and the evaluation parameter by the evaluation parameter unit, and integrating multiple path coefficients in the theoretical causal path diagram corresponding to the relationship between the basic parameters and the evaluation parameter to obtain the action intensity; For the same evaluation parameter, determine the weight of each evaluation parameter according to the coefficient of variation and the action intensity.

[0037] In this embodiment, each evaluation parameter corresponds to a relationship between a basic parameter and the evaluation parameter. A calibration value is determined according to the coefficient of variation and the action intensity, and the weights are assigned by comparing the calibration values of all evaluation parameters. The calculation formula of the calibration value is as follows: ;

[0038] Where is the calibration value of the th evaluation parameter, is the action intensity of the th evaluation parameter, is the coefficient of variation of the th evaluation parameter, is the first constant of the th evaluation parameter, represents the correction of the coefficient of variation to the action intensity, and the coefficient of variation describes the reliability and stability of the evaluation parameter.

[0039] In this embodiment, the stable level of the processing condition is defined according to the fluctuation of the basic parameters, and the stable level of the processing condition is determined in combination with the coefficients of variation of all basic parameters. Here, there are two coefficients of variation of the basic parameters, one is the real-time coefficient of variation, and the other is the coefficient of variation determined by the historical data of the parameter, which are respectively recorded as the first coefficient of variation and the second coefficient of variation. Compare the two to determine a variation evaluation value (describing the stable situation compared with the previous variation situation), and determine the stable level of the processing condition based on the variation evaluation value of each basic parameter. The calculation formula is as follows: ;

[0040] Where is the stable level of the processing condition, is the number of basic parameters, is the combined weight of the th basic parameter, is the variation evaluation value of the th basic parameter, is the maximum value in, , They are the second constant and the third constant respectively (used to balance the size and level of the correction function). It represents the correction of the maximum value to the class average, and the class average should be slightly larger than the ordinary average value. [] is the rounding symbol.

[0041] In step S103, the weights of the evaluation parameters are dynamically adjusted by processing the operating condition stability level, a multi-objective optimization model is constructed, the inertia weight in the MOPSO algorithm is set, and the optimal solution of the multi-objective optimization model is solved by the MOPSO algorithm.

[0042] In this embodiment, the significance of multi-objective optimization is as follows: Solving conflicting objectives: For example, minimizing both the effluent COD and energy consumption simultaneously, and there is usually a trade-off between the two.

[0043] Providing decision support: Generating the Pareto front for decision-makers to select the optimal solution according to their preferences.

[0044] Enhancing system robustness: Avoiding sub-optimal solutions caused by single objectives through multi-objective optimization.

[0045] The significance of solving by the MOPSO algorithm: Applicable to continuous / discrete problems: Flexibly handling mixed variables in sewage treatment (such as continuous aeration volume, discrete equipment switches).

[0046] Efficiently searching for the Pareto front: Rapidly approaching the optimal solution set through particle swarm cooperation.

[0047] Dynamic adaptability: Combining inertia weight adjustment to adapt to changes in operating conditions. The size of the inertia weight in the MOPSO algorithm (balancing global and local search capabilities to ensure the quality of the solution and the solving speed).

[0048] Framework process: Input: Real-time data of basic parameters (DO, MLSS, aeration volume).

[0049] Step 1: Calculate the operating condition stability level (high / medium / low stability).

[0050] Step 2: Dynamically adjust the weights of the evaluation parameters according to the stability level.

[0051] Step 3: Construct a multi-objective optimization model (such as effluent quality, energy consumption, operating cost).

[0052] Step 4: Set the inertia weight of the MOPSO algorithm and solve for the optimal solution.

[0053] Output: The Pareto optimal solution set to support decision-making selection.

[0054] The process of the MOPSO algorithm: Initialize the particle swarm: Randomly generate particle positions (decision variable values) and velocities.

[0055] External archive maintenance: Store non-dominated solutions (Pareto frontiers).

[0056] Iterative update: Calculate the objective function values of each particle.

[0057] Update the personal best solution (pbest) and the global best solution (gbest, selected based on crowding distance). Update the particle velocities and positions; Termination condition: Reach the maximum number of iterations or the Pareto front converges.

[0058] In some embodiments of the present application, the weights of evaluation parameters are dynamically adjusted by processing the stability level of the working condition, including, Judge whether the current sewage treatment working condition belongs to a stable state based on the stability level of the working condition; If the current sewage treatment working condition belongs to a stable state, there is no need to adjust the weights of the evaluation parameters; Otherwise, adjust the weights of the evaluation parameters according to the relationship between the basic parameters and the evaluation parameters.

[0059] In this embodiment, the stability level of the working condition is used to describe the stability of the current sewage treatment working condition, so as to judge whether adjustment is needed, ensuring the reliability of multi-objective optimization. Precise regulation: Only adjust the weights when the working condition is unstable, avoiding excessive interference. Strong adaptability: Combine real-time data with process mechanisms to dynamically match operation requirements.

[0060] In some embodiments of the present application, a multi-objective optimization model is constructed, including, Taking each evaluation parameter as a unit, based on the relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters, construct the objective function of each evaluation parameter, and synthesize the objective functions of all evaluation parameters to generate a comprehensive objective function model; Collect multiple types of constraint factors required for the sewage treatment process, and determine the constraint conditions of the parameters in the multi-objective optimization model according to the multiple types of constraint factors.

[0061] In this embodiment, the objective functions of all evaluation parameters are synthesized by weighted summation. Multiple types of constraint factors include process constraints, water quality constraints, equipment constraints, safety constraints, etc. The constraint conditions of the parameters in the multi-objective optimization model, where the parameters here are controllable parameters.

[0062] In some embodiments of the present application, set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm, including, Based on the two functional relationships, namely the functional relationship between the basic parameters and the functional relationship between the basic parameters and the evaluation parameters, local sensitivity analysis and global sensitivity analysis are respectively carried out, and the sensitive indicators are determined by combining the results of the two sensitivity analyses. Analyze the correlation between evaluation parameters to determine the conflict indicators of evaluation parameters, determine the inertia weight according to the sensitive indicators and conflict indicators, and thus implement the MOPSO algorithm to calculate the optimal solution of the multi-objective optimization model.

[0063] In this embodiment, the inertia weight is affected by both the data sensitivity degree and the conflict situation of evaluation parameters. Considering both, a reasonable inertia weight is determined to balance the global and local search capabilities. Improve the search efficiency: Dynamically adjust the inertia weight according to the conflict degree to avoid falling into local optima. Example: Expand the search range when the conflict is high and perform fine optimization when the conflict is low. Enhance the solution quality: Combine the sensitivity of basic parameters and prioritize the optimization of key parameters. Example: When DO is sensitive to the effluent COD, adjust the DO value more precisely. Adapt to complex systems: Applicable to complex systems with multiple objectives and strong coupling (such as sewage treatment). Example: Multi-objective optimization of effluent quality, energy consumption, and chemical agent cost. Automation and robustness: Reduce the need for manual parameter adjustment and improve the robustness of the algorithm. Example: Automatically adapt to conflicts and sensitivity changes under different working conditions.

[0064] In this embodiment, the purpose of local sensitivity analysis is to quantify the impact of small changes in a single basic parameter within a local range on the evaluation parameter. It is realized by the partial derivative method, that is, calculating the partial derivative of the objective function with respect to the basic parameter to evaluate the local sensitivity. Global sensitivity analysis evaluates the comprehensive impact of basic parameters on evaluation parameters within the entire feasible domain. Sobol index method: Decompose the variance of the objective function and calculate the main effects and interaction effects of each parameter. Combine the results of the two sensitivity analyses (local sensitivity analysis and global sensitivity analysis) to determine the sensitive indicators, calculate the Pearson correlation coefficient between evaluation parameters, and determine the conflict indicators of evaluation parameters. Determine the inertia weight jointly according to the sensitive indicators and conflict indicators.

[0065] Step S104, set an adaptive control strategy, and coordinately regulate the sewage process parameters based on the adaptive control strategy and the optimal solution of the multi-objective optimization model.

[0066] In this embodiment, the idea is as follows: Dual-objective interval generation: Adaptive control strategy: Dynamically output the first control objective interval based on the real-time working conditions.

[0067] Multi-objective optimization model: Output the second control objective interval based on the Pareto optimal solution set.

[0068] Interval coordination mechanism: Intersection Priority: If there is an intersection between two intervals, directly use the intersection for parameter regulation.

[0069] Deviation Compensation: If there is no intersection, dynamically adjust the regulation strategy according to the interval deviation.

[0070] In some embodiments of the present application, the sewage process parameters are coordinately regulated based on the optimal solutions of the adaptive control strategy and the multi-objective optimization model, including, Output the first control target interval according to the adaptive control strategy, and output the second control target interval according to the optimal solution of the multi-objective optimization model; If there is an intersection between the first control target interval and the second control target interval, then use the intersection of the control target intervals to regulate the sewage process parameters; Otherwise, regulate the sewage process parameters according to the deviation between the first control target interval and the second control target interval.

[0071] In this embodiment, fuzzy logic control is used as the adaptive control strategy. Dynamic compensation is performed according to the deviation situation. The weighted average value is used for small deviations, and the lower limit of the second control target interval is used for large deviations. The adaptive strategy real-time corrects the deviation, and the model provides a fault tolerance interval to avoid the failure of single-point control and enhance the anti-interference ability. Adaptive control strategy: Real-time response: Dynamically adjust parameters according to real-time working conditions (such as influent load, equipment status) to ensure the stable operation of the system. Local optimization: Quickly respond to sudden working conditions (such as a sudden increase in influent COD during the rainstorm period) to avoid system collapse.

[0072] Correspondingly, the present application also provides a sewage process parameter regulation system based on artificial intelligence, such as Figure 2 shown including, The first module is used to collect all sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, the sewage process parameters include basic parameters and evaluation parameters, and analyze the interaction relationships between the basic parameters and the influence of the basic parameters on the evaluation parameters; The second module is used to count the fluctuation situations of the basic parameters and the evaluation parameters, and set the weight of each evaluation parameter in combination with the influence of the basic parameters on the evaluation parameters, and define the stable level of the treatment working condition according to the fluctuation situation of the basic parameters; The third module is used to dynamically adjust the weight of the evaluation parameter through the stable level of the treatment working condition, construct a multi-objective optimization model, set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm; The fourth module is used to set the adaptive control strategy and coordinately regulate the sewage process parameters based on the optimal solutions of the adaptive control strategy and the multi-objective optimization model.

[0073] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Analyze the interaction relationships between the basic parameters and the relationship between the basic parameters and the evaluation parameters, accurately analyze the relationships between the basic parameters and between the basic parameters and the evaluation parameters, and provide a reliable basis for subsequent multi-objective optimization and regulation. Set the weight of each evaluation parameter by combining the relationship between the basic parameters and the evaluation parameters and the fluctuation of the evaluation parameters, improve the adaptability and stability of multi-objective optimization, and balance the requirements of multiple objectives as much as possible. Dynamically adjust the weight of the evaluation parameter by processing the working condition stability level, monitor the sewage treatment working condition, and judge whether the weight of the multi-objective parameter needs to be adjusted, so as to adjust in time and ensure timeliness.

[0074] 2. Set the inertia weight in the MOPSO algorithm, and solve the optimal solution of the multi-objective optimization model through the MOPSO algorithm, balance the local and global search capabilities, and improve the quality of the optimal solution. Cooperatively regulate the sewage process parameters based on the optimal solution of the adaptive control strategy and the multi-objective optimization model, combine adaptive control and multi-objective optimization, comprehensively and effectively improve the regulation effect of the process parameters, improve the accuracy and adaptability of the sewage process parameter regulation, and ensure the balance between multiple objectives of sewage treatment and the sewage treatment effect.

[0075] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (such as a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0076] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0077] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more systems different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0078] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, making equivalent substitutions or changes, shall be covered by the protection scope of the present invention.

Claims

1. A sewage process parameter control method based on artificial intelligence, characterized in that: include, Collect all sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, including basic parameters and evaluation parameters, and analyze the relationship between basic parameters and the relationship between basic parameters and evaluation parameters; Calculate the fluctuation of basic parameters and evaluation parameters, set the weight of each evaluation parameter based on the relationship between basic parameters and evaluation parameters, and define the stability level of the processing condition according to the fluctuation of basic parameters; By processing the stability level of the working condition, the weights of the evaluation parameters are dynamically adjusted, a multi-objective optimization model is constructed, the inertia weight in the MOPSO algorithm is set, and the optimal solution of the multi-objective optimization model is solved by the MOPSO algorithm; An adaptive control strategy is set, and the sewage process parameters are coordinated and regulated based on the optimal solution of the adaptive control strategy and the multi-objective optimization model.

2. The artificial intelligence-based sewage process parameter control method according to claim 1, characterized in that: Analyze the relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters, including: Multiple regression analysis was used to analyze the relationship between different basic parameters, and significant relationships were screened based on P values; According to the sewage treatment mechanism model, a hypothetical causal path between basic parameters and evaluation parameters is given, and a theoretical causal path diagram is constructed. The nodes in the theoretical causal path diagram are basic parameters or evaluation parameters, and the edges or paths represent the relationship between basic parameters or the relationship between basic parameters and evaluation parameters; Calculate the path coefficient of each path and mark it at the corresponding position of the theoretical causal path diagram. Divide the direct effect relationship and indirect effect relationship according to the proximity relationship between the nodes on the theoretical causal path diagram. Based on the path coefficient, direct effect relationship and indirect effect relationship, determine the effect relationship of the basic parameter on the evaluation parameter.

3. The artificial intelligence-based sewage process parameter control method according to claim 2, characterized in that: Fluctuations of statistical basic parameters and evaluation parameters, including: The standard deviation and mean value of the basic parameters and evaluation parameters are calculated, and the coefficient of variation of the basic parameters and evaluation parameters is calculated based on the standard deviation and mean value. The coefficient of variation is used to describe the fluctuation of the basic parameters and evaluation parameters.

4. The artificial intelligence-based sewage process parameter control method according to claim 3, characterized in that: And the weight of each evaluation parameter is set based on the relationship between the basic parameters and the evaluation parameters. include, The effect relationship between multiple groups of basic parameters and evaluation parameters is divided into units of evaluation parameters, and multiple path coefficients in the theoretical causal path diagram corresponding to the effect relationship between basic parameters and evaluation parameters are integrated to obtain the effect strength; For the same evaluation parameter, the weight of each evaluation parameter is determined according to the coefficient of variation and the intensity of action.

5. The artificial intelligence-based sewage process parameter control method according to claim 3 is characterized in that: Dynamically adjust the weights of evaluation parameters by processing the stability level of working conditions, include, Determine whether the current sewage treatment condition is stable by the treatment condition stability level; If the current sewage treatment condition is stable, there is no need to adjust the weight of the evaluation parameters; Otherwise, the weight of the evaluation parameter is adjusted according to the relationship between the basic parameter and the evaluation parameter.

6. The artificial intelligence-based sewage process parameter control method according to claim 1, characterized in that: Construct a multi-objective optimization model, including, Taking each evaluation parameter as a unit, construct the objective function of each evaluation parameter based on the interaction between basic parameters and the interaction between basic parameters and evaluation parameters, and synthesize the objective functions of all evaluation parameters to generate a comprehensive objective function model; Collect multiple types of constraint factors required for the sewage treatment process, and determine the constraint conditions of parameters in the multi-objective optimization model based on the multiple types of constraint factors.

7. The artificial intelligence-based sewage process parameter control method according to claim 1, characterized in that: Set the inertia weight in the MOPSO algorithm and use the MOPSO algorithm to find the optimal solution for the multi-objective optimization model. include, Based on the two relationships between the basic parameters and the relationship between the basic parameters and the evaluation parameters, local sensitivity analysis and global sensitivity analysis are carried out respectively, and the sensitive indicators are determined by combining the results of the two sensitivity analyses. The correlation between the evaluation parameters is analyzed to determine the conflict index of the evaluation parameters, and the inertia weight is determined according to the sensitive index and the conflict index, so as to implement the MOPSO algorithm and calculate the optimal solution of the multi-objective optimization model.

8. The artificial intelligence-based sewage process parameter control method according to claim 1, characterized in that: Based on the optimal solution of adaptive control strategy and multi-objective optimization model, the sewage process parameters are coordinated and controlled, including: Outputting a first control target interval according to an adaptive control strategy and outputting a second control target interval according to an optimal solution of a multi-objective optimization model; If there is an intersection between the first control target interval and the second control target interval, the intersection of the control target intervals is used to control the sewage process parameters; Otherwise, the sewage process parameters are adjusted according to the deviation between the first control target interval and the second control target interval.

9. The artificial intelligence-based sewage process parameter control system is characterized by: include, The first module is used to collect all sewage process parameters involved in the sewage treatment process, classify the sewage process parameters, which include basic parameters and evaluation parameters, and analyze the relationship between the basic parameters and the relationship between the basic parameters and the evaluation parameters; The second module is used to calculate the fluctuation of basic parameters and evaluation parameters, and set the weight of each evaluation parameter based on the relationship between the basic parameters and the evaluation parameters, and define the stability level of the processing condition according to the fluctuation of the basic parameters; The third module is used to dynamically adjust the weights of evaluation parameters by processing the working condition stability level, build a multi-objective optimization model, set the inertia weight in the MOPSO algorithm, and solve the multi-objective optimization model with the MOPSO algorithm; The fourth module is used to set the adaptive control strategy and coordinately regulate the sewage process parameters based on the optimal solution of the adaptive control strategy and the multi-objective optimization model.

Images