Intelligent decision fusion system for multi-stage process cooperation of sewage plant

Abstract

The invention discloses a sewage plant multi-process-section collaborative intelligent decision fusion system, which comprises a sensing and rule fusion layer used for collecting inlet and outlet water quality parameters, process control parameters and operation state parameters of multiple process sections in real time, preprocessing data and fusing an expert rule base; the mechanism and data driving joint modeling layer is used for establishing a mechanism model and a data driving model under the constraint condition of the expert rule base and predicting control quantities respectively; and the collaborative optimization and fusion decision-making layer is used for executing cross-process-section multi-target collaborative optimization and fusion decision-making based on an output result of the mechanism and data driving joint modeling layer under the constraint condition of an expert rule base, calculating a dynamic fusion weight, generating a final control quantity, and issuing the final control quantity to execution equipment. And in combination with real-time feedback self-adaptive adjustment, closed-loop optimization is realized. According to the system, the sewage treatment stability, decision precision and resource utilization efficiency are improved, and the environmental risk is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of sewage treatment and artificial intelligence, and particularly relates to an intelligent decision fusion system for multi-section process coordination of a sewage plant. BACKGROUND

[0002] A sewage treatment plant is an important infrastructure for ensuring urban water environmental quality and water resource safety, and its operation efficiency and effluent water quality stability are directly related to environmental protection and social sustainable development.

[0003] A typical sewage treatment plant usually includes a pretreatment section, a biochemical treatment section, a deep treatment section, and a sludge treatment section, and there is a significant material and energy coupling relationship between each unit, and the operation adjustment presents characteristics such as multivariable, strong coupling, nonlinearity, and time-varying.

[0004] In actual operation, the control system not only needs to ensure that the effluent water quality is stable and meets the standards for a long time, but also needs to consider economic and environmental targets such as energy consumption, chemical consumption, and sludge production, to achieve comprehensive optimization of multiple targets.

[0005] At present, the decision-making models of different process sections of the sewage plant are usually operated independently, but in actual operation, the operating states of each process section affect each other, for example, the dissolved oxygen adjustment of the aeration system not only affects the organic matter removal effect of the biochemical section, but also has an effect on the load and energy consumption of the subsequent deep treatment section. If there is a lack of global coordinated optimization, local optimization often sacrifices the overall performance.

[0006] At the same time, the application of real-time feedback in control optimization is also relatively limited, and the existing methods usually only perform simple error correction, lack a closed-loop adaptive mechanism combining short-term rapid adjustment and long-term strategy optimization, and are difficult to achieve optimal operation continuously and stably under different time scales and working conditions. SUMMARY

[0007] The purpose of the present application is to provide an intelligent decision fusion system for multi-section process coordination of a sewage plant, to realize multi-target optimization decision and dynamic fusion control across process sections.

[0008] To address this, the present invention provides an intelligent decision-making fusion system for multi-process stage collaboration in wastewater treatment plants, comprising a perception and rule fusion layer, a mechanism and data-driven joint modeling layer, and a collaborative optimization and fusion decision layer. The perception and rule fusion layer collects in-process and effluent water quality parameters, process control parameters, and operating status parameters in real time from the pretreatment, biochemical treatment, advanced treatment, and sludge treatment stages of the wastewater treatment plant, preprocesses the data, and integrates it with an expert rule base. The mechanism and data-driven joint modeling layer establishes a mechanism model and a data-driven model under the constraints of the expert rule base. The mechanism model performs process stage simulation prediction and outputs mechanism-predicted control quantities, while the data-driven model makes predictions and outputs AI-predicted control quantities. The collaborative optimization and fusion decision layer, under the constraints of the expert rule base, performs multi-objective collaborative optimization and fusion decision-making across process stages based on the output of the mechanism and data-driven joint modeling layer, calculates dynamic fusion weights, generates final control quantities, distributes the final control quantities to the execution equipment, and achieves closed-loop optimization through real-time feedback and adaptive adjustment.

[0009] This invention integrates multi-source sensing, dual-model prediction, cross-segment optimization, and closed-loop execution technologies to upgrade the "segmented management" model of wastewater treatment plants to a "full-process collaborative control" model, leading wastewater treatment plants towards digitalization and intelligence. The application of this system can reduce environmental risks and resource waste throughout the entire process, providing key technical support for wastewater treatment plants to achieve high-quality, low-carbon, and intelligent operation goals.

[0010] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description

[0011] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0012] Fig. 1 This is a structural block diagram of the intelligent decision-making fusion system for multi-stage process coordination in wastewater treatment plants according to the present invention;

[0013] Fig. 2 This is a schematic diagram of the multi-process segment collaborative optimization process of the present invention;

[0014] Fig. 3 This is a schematic diagram of the decision fusion process of the intelligent decision fusion system of the present invention. Detailed Implementation

[0015] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0016] Combined with referenceFigs. 1 to 3 The sewage plant multi-process section synergistic intelligent decision fusion system comprises a perception and rule fusion layer, a mechanism and data-driven joint modeling layer, and a synergistic optimization and fusion decision layer.

[0017] The perception and rule fusion layer is used for collecting water quality parameters, process control parameters and operation state parameters in real time from the pretreatment section, the biochemical treatment section, the advanced treatment section and the sludge treatment section of the sewage plant, performing preprocessing such as cleaning, standardization, time sequencing and alignment on the data, and fusing an expert rule base constructed based on expert experience and process specifications to provide safety boundaries and constraint conditions for model operation.

[0018] The mechanism and data-driven joint modeling layer is used for establishing a mechanism model and a data-driven model under the constraint conditions of the expert rule base, the mechanism model simulates the operation state of each process section based on material balance and kinetic equation and outputs mechanism prediction control, and the data-driven model constructs a deep learning prediction structure based on historical multivariate time series and outputs AI prediction control.

[0019] The synergistic optimization and fusion decision layer is used for performing multi-objective synergistic optimization and dynamic fusion weight calculation on the mechanism prediction control and the AI prediction control under the constraint conditions of the expert rule base, generating a final control and issuing it to an execution device, and simultaneously performing closed-loop adaptive adjustment combined with real-time feedback to realize short-term rapid adjustment and long-term strategy optimization.

[0020] The synergistic optimization and fusion decision layer is the core of the system. This layer fuses the mechanism prediction control and the AI prediction control, calculates the final control and issues it to the execution device.

[0021] In the optimization process, the system comprehensively considers multiple targets such as water quality compliance, energy consumption and reagent consumption, and adopts a multi-objective weighted sum method for optimization. The system also has a dynamic fusion weight mechanism, which prioritizes the use of AI prediction control when the AI model accuracy is high, and falls back to the mechanism model control when the prediction error increases, ensuring stable operation of the system. This layer also automatically adjusts the control strategy according to real-time feedback through closed-loop adaptive adjustment, ensuring the adaptability and robustness of the system under different working conditions, and improving the operation efficiency and water quality stability of the sewage plant.

[0022] The working process of the perception and rule fusion layer includes the following steps S11 and S12.

[0023] S11, collect multi-source perception data and perform preprocessing; the perception data includes water quality parameters, process control parameters and operation state parameters.

[0024] S12, based on expert experience and process operation specification, generate an expert rule library containing safety threshold, logical constraint and trigger condition, to provide safety boundary for subsequent model calculation.

[0025] In the present application, after the collection of perception data is completed by means of the automatic sampling detection system, the collected perception data is preprocessed in combination with the functions of the related data processing software and the practical experience of manual preprocessing.

[0026] In specific implementation, the process of preprocessing the multi-source perception data in step S11 includes the following steps S111-S113.

[0027] S111, a perception data cleaning step, including removing noise, processing missing values and abnormal values.

[0028] By filtering noise, filling missing values and processing abnormal values of the multi-source perception data, the distortion problems caused by sensor errors, transmission interference or sudden working conditions in the data collection process are eliminated, ensuring the basic integrity and reliability of the perception data, and providing a high-quality data source for subsequent processing.

[0029] S112, a perception data standardization step, including performing zero-mean unit variance standardization processing.

[0030] The perception data after data cleaning is planned and processed, and the z-score standardization method of zero-mean unit variance standardization is used to unify the scale of the cleaned data. By converting the perception data of different magnitudes and dimensions into standard normal distribution data with a mean of 0 and a standard deviation of 1, the influence of the scale difference between features on model training is eliminated, avoiding the dominance of model prediction results due to the too large numerical range of a certain type of parameters, and ensuring that each feature has equal influence in subsequent modeling.

[0031] S113, a perception data time sequencing step, including constructing a multi-time step sequence in chronological order and generating a sliding window sample.

[0032] According to the time sequence characteristics of the sewage treatment process, the perception data after standardization is sorted according to the collection time stamp to construct continuous time sequence data. The sliding window technology is used to divide the data into multiple time windows, each time window containing a number of time step data samples, and the window is sampled to generate multiple groups of time sequence sample data through continuous sliding window.

[0033] S114, a perception data alignment step, including interpolating and filling the data of different sampling frequencies and time references and performing time stamp unification processing.

[0034] The data of different sampling frequencies and time bases are interpolated and timestamped, and the time marks of each data source are calibrated through a unified timestamp basis, so that the perception data collected at different times are strictly aligned in the time dimension.

[0035] In a specific implementation, in step S12, the expert experience and process specifications are converted into a rule parameter set, including the safety threshold range of the key control variables of each process section, the logical constraint relationship between the variables, and the abnormal condition triggering condition, and the rule parameter set is stored in the expert rule library for calling by the mechanism model and the data-driven model, so as to provide safety boundary constraints, running state monitoring and out-of-bound early warning functions in the model running process.

[0036] In a specific implementation, the working process of the mechanism and data-driven joint modeling layer includes the following steps:

[0037] S21, establishing a mechanism model and a data-driven model under the constraint condition of the expert rule library;

[0038] S22, the mechanism model performs process section simulation prediction and outputs a mechanism prediction control variable;

[0039] S23, the data-driven model performs prediction and outputs an AI prediction control variable.

[0040] The mechanism and data-driven joint modeling layer is constructed based on the mechanism model, the data-driven model and the expert rule library, and provides double prediction control basis for the wastewater treatment process.

[0041] The working of the mechanism and data-driven joint modeling layer includes three parts: the construction and simulation prediction of the mechanism model, that is, simulating the physical, chemical and biological reactions of each process section based on material balance and kinetic equations, and outputting a mechanism prediction control variable; the training and prediction of the data-driven model, that is, learning the regularity of historical time series data by using a deep learning network, and outputting an AI prediction control variable; and realizing parallel cooperation of the two types of models under the constraint of the expert rule library, ensuring that the prediction control variable is within the safe operation range, and providing reliable basic data for subsequent optimization decision-making.

[0042] In step S21, the mechanism model and the data-driven model are established based on the constraint condition of the expert rule library. The mechanism model is used to describe and depict the physical, chemical and biological reaction mechanisms in the wastewater treatment process; and the data-driven model is used to depict the nonlinear mapping relationship between the input features and the target control variable.

[0043] Mechanism models are used to characterize and describe the physical, chemical, and biological reaction mechanisms in wastewater treatment. They quantify processes such as flocculation and sedimentation in the pretreatment stage, microbial metabolism in the biochemical stage, and reagent reactions in the advanced treatment stage through material balance equations and reaction kinetic equations. Safety thresholds in the expert rule base are used as boundary conditions for the model, providing a theoretical explanation and a basis for stable prediction of the process essence for the system.

[0044] The data-driven model is used to characterize the nonlinear mapping relationship between input features and target control quantities. It constructs a deep learning network based on time series prediction structure, takes multivariate time series data output from the perception and rule fusion layer as input, and uses logical constraints in the expert rule base as training boundaries. By learning the hidden patterns in historical operation data, it accurately captures the complex nonlinear correlation between process variables and realizes dynamic prediction of control quantities.

[0045] In specific implementation, in step S22, the mechanism model is constructed based on the material balance and kinetic equations and the operating mechanism of each process segment, and the operating status of each process segment is simulated in real time, and the mechanism prediction control quantity is output.

[0046] In the system of this invention, the mechanistic model integrates the core operational laws of each process stage in wastewater treatment, including the kinetics of bar screen interception and grit settling in the pretreatment stage, the reaction mechanism of activated sludge in the biological treatment stage, the chemical coagulation and adsorption laws in the advanced treatment stage, and the dewatering and drying characteristics in the sludge treatment stage. By combining the mass balance equation with the reaction kinetic equation, a dynamic simulation model covering the entire process is constructed. This model can calculate in real time the changes of key parameters in each process stage under different operating conditions, such as dissolved oxygen concentration in the aeration tank, sludge interface height in the sedimentation tank, and head loss in the filter. Based on this, corresponding mechanistic predictive control quantities are output, such as aeration rate adjustment values, chemical dosage baselines, and sludge return ratios. This process-based modeling approach can maintain predictive stability under complex operating conditions, providing the system with control basis that conforms to the core laws of wastewater treatment, and supporting the scientific and reliable nature of the decision-making process.

[0047] In specific implementation, in step S23, the data-driven model is constructed based on historical multivariate time series data, and a deep learning network based on time series prediction structure is used to output AI predictive control quantities.

[0048] In the system of this invention, the data-driven model is based on historical operational data of multiple process sections processed by the perception and rule fusion layer, covering multi-dimensional time-series data such as influent and effluent water quality parameters, process control parameters, and operational status parameters. By constructing a deep learning network suitable for time series prediction, the historical data is transformed into input feature sequences and target control variable labels using the sliding window method. With safety thresholds and logical constraints in the expert rule base as training boundaries, the network parameters are iteratively optimized through the backpropagation algorithm, enabling the model to learn the hidden dynamic correlation patterns in the data.

[0049] In real-time operation, the model receives the latest multivariate time series data, and after feature extraction and pattern matching, outputs dynamic AI predictive control quantities for each process section, such as refined aeration volume adjustment values ​​based on influent fluctuations and reagent dosage correction amounts based on effluent water quality trends, thereby achieving accurate dynamic prediction of the process and making up for the limitations of mechanistic models in dealing with complex nonlinear operating conditions.

[0050] Through the above steps S21-S23, the mechanism and data-driven joint modeling layer organically integrates the mechanism model, the data-driven model, and the expert rule base. Through dual modeling, parallel prediction, and boundary constraints, it provides control outputs that are both theoretically based and data-supported for collaborative optimization decision-making.

[0051] Based on sensing data and historical operating patterns, the system can simultaneously generate mechanism-based predictive control quantities and AI-based predictive control quantities. These quantities not only conform to the core reaction mechanism of wastewater treatment but also capture the nonlinear dynamic characteristics under complex operating conditions, and all remain within the safe operating range defined by the expert rule base.

[0052] The application of the mechanism-driven and data-driven joint modeling layer not only ensures the stability and interpretability of predictive control, but also improves its adaptability and accuracy to complex operating conditions, providing a reliable dual predictive basis for subsequent collaborative optimization and fusion decision-making, and supporting the intelligent control of the wastewater treatment process.

[0053] In practice, the collaborative optimization and fusion decision-making process includes the following steps:

[0054] S31. Perform cross-process multi-objective collaborative optimization under the constraints of the expert rule base;

[0055] S32. Dynamically fusion weights of mechanistic predictive control and AI predictive control to generate fused control;

[0056] S33. The integrated control quantity is issued and executed, and closed-loop optimization is achieved by adaptive adjustment based on feedback.

[0057] The collaborative optimization and fusion decision layer is the core execution part of the intelligent decision fusion system for wastewater treatment. It is based on a multi-objective collaborative optimization and dynamic fusion weight mechanism across process stages and a closed-loop feedback adjustment strategy to achieve the optimization of the wastewater treatment process.

[0058] The work of the collaborative optimization and fusion decision layer includes three parts: multi-objective collaborative optimization, dynamic adjustment of mechanism and data-driven models, fusion weight generation of control variables, and closed-loop feedback and adaptive adjustment.

[0059] In specific implementation, step S31 involves performing cross-process multi-objective collaborative optimization under the constraints of the expert rule base. Taking into account objectives such as effluent quality compliance rate, energy consumption, and reagent dosage, a multi-objective optimization weighted sum method is used to set weights and objective functions for multi-objective optimization. The optimization objective function is as follows:

[0060]

[0061] Where Z is the overall optimization objective value; w i Let be the weight coefficient of the i-th objective, satisfying and ; Let i be the optimization objective function; Let be the i-th control vector; n is the number of optimization objectives.

[0062] Collaborative optimization employs a constrained multi-objective optimization algorithm, using Newton's iteration method to iteratively update the control input. The control input update formula is:

[0063]

[0064] in, The control vector for the dth iteration; For the joint cost function; It is the first-order gradient vector, that is, the partial derivatives of each control variable with respect to the overall target; It is the second-order Hessian matrix, i.e., the second-order partial derivative; The learning rate is adaptive and dynamically adjusted based on the iteration step size.

[0065] In specific implementation, in step S32, based on the results of multi-objective collaborative optimization control, the mechanism prediction control quantity of the collaborative optimization output is... AI predictive control quantity The formula for dynamically adjusting the fusion weights can be expressed as follows:

[0066]

[0067] in, is the weighting adjustment coefficient; E is the real-time feedback error, which is the weighted sum of the deviations between the actual and predicted values ​​of key indicators in the process section. The maximum allowable error threshold; To improve the accuracy of AI model predictions; when hour, Only use To ensure safety.

[0068] The final control quantity is obtained after dynamic weighted fusion. The final control quantity fusion formula is:

[0069]

[0070] in, For dynamic fusion weights, range ; This is the final control quantity to be issued and executed; Mechanism predictive control inputs for collaborative optimization of output; To collaboratively optimize the output of AI predictive control variables.

[0071] This dynamic fusion weighting mechanism ensures that the optimized results are prioritized when the AI ​​model has high accuracy and low error, while gradually reverting to the mechanistic model control quantity when the prediction error increases or the operation becomes unstable, so as to ensure operational safety and water quality stability.

[0072] In specific implementation, in step S33, the final fused control quantity will be... The command is sent to the corresponding device for execution, and execution feedback signals are collected in real time. and the target set value The deviation is calculated, and closed-loop optimization is achieved through adaptive adjustment based on feedback. The formula for calculating the feedback deviation is:

[0073]

[0074] in, Set a value for the target; This is the actual execution feedback value; This represents the control deviation at the current moment.

[0075] Closed-loop optimization is performed based on the deviation. The closed-loop control adopts proportional-integral-derivative (PID) regulation, and the calculation formula is as follows:

[0076]

[0077] in, For feedback adjustment signal; This is a proportionality coefficient, reflecting the intensity of the immediate response to the deviation; These are the integral coefficients used to eliminate steady-state errors; These are the differential coefficients, used to suppress rapid fluctuations in the system; This is the rate of change of deviation, used to predict deviation trends in advance.

[0078] Simultaneously, based on closed-loop optimization, an adaptive adjustment mechanism is introduced to update the dynamic fusion weights and optimization model parameters according to the feedback error trend, forming a short-term fast adjustment loop and a long-term strategy optimization loop, dynamically updating the fusion weights. AI model hyperparameters and the sensitivity coefficient of the mechanism model This ensures the stability and robustness of control performance under different operating conditions.

[0079] Based on real-time comprehensive error, with periods ranging from minutes to hours. AI accuracy The fusion weights are dynamically adjusted to achieve a short-term, rapid adjustment loop. The calculation formula is as follows:

[0080]

[0081] in, The fusion weight at the current moment, with a value range of [0,1]; To integrate the weight update step size and control the rate of weight change; For real-time comprehensive error; The maximum permissible composite error threshold; This is a metric for the accuracy of AI models within the most recent prediction window.

[0082] The AI ​​model hyperparameters are updated daily or weekly based on historical operating data and feedback evaluation results to achieve a long-term strategy optimization loop for the AI ​​model hyperparameters. The calculation formula is as follows:

[0083]

[0084] in, represents the hyperparameters of the AI ​​model; m represents the number of long-term optimization iterations. Update the learning rate for hyperparameters; For AI model hyperparameters Gradient computation operator, This is the loss function for the AI ​​model.

[0085] Parameter correction amount of computer theoretical model based on feedback data And update the sensitivity coefficient to achieve adaptive correction of the sensitivity coefficient of the mechanistic model. The calculation formula is as follows:

[0086]

[0087] in, This is a set of sensitivity coefficients for the mechanistic model, including reaction rate constants, conversion efficiency parameters, etc. Update the step size for sensitivity; This is the sensitivity correction amount calculated based on the feedback data.

[0088] This invention, at the collaborative optimization and fusion decision-making level, combines multi-objective optimization across process segments, dynamic fusion of dual models, and closed-loop adaptive adjustment to balance objectives such as water quality, energy consumption, and reagent dosage. It employs a multi-objective optimization algorithm to iteratively optimize the control quantity, calculates the fusion weight in real time to generate the final control quantity, and achieves full-process closed-loop optimization based on PID regulation and model parameter updates, ensuring efficient collaboration among various process segments.

[0089] The intelligent decision-making fusion system of this invention enables intelligent collaborative operation of the entire wastewater treatment plant process, covering multi-process optimization, cross-process operation monitoring, and global anomaly early warning. This invention has the following technical features / advantages:

[0090] 1. The intelligent decision-making fusion system of this invention can monitor key operating parameters of multiple process stages in a wastewater treatment plant in real time. The system collects data in real time through automatic sampling and intelligent sensors, and combines multi-source data preprocessing with an expert rule base to provide accurate water quality predictions and anomaly warnings, ensuring rapid response and reducing potential risks in emergency situations.

[0091] 2. The intelligent decision-making fusion system of this invention supports multi-process segment linkage intelligent control. It not only ensures the stable operation of individual process segments but also achieves overall optimization of the entire process, significantly improving the anti-interference capability and operational reliability of the processing system.

[0092] 3. The intelligent decision fusion system of this invention provides intelligent decision support throughout the entire process. It can autonomously adjust the control strategy under different operating conditions to achieve the optimal configuration of the wastewater treatment process, ensuring treatment effect and operational stability.

[0093] 4. The intelligent decision-making fusion system of this invention features end-to-end low-carbon and environmentally friendly characteristics. It prioritizes low-energy-consumption operating parameters through a multi-objective optimization algorithm, reducing ineffective energy consumption. Simultaneously, the system can monitor the pollutant removal efficiency and final emission indicators of each process stage in real time, ensuring that the treatment process meets environmental standards.

[0094] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent decision fusion system for the coordination of multiple process units in a wastewater treatment plant, characterized in that, comprise a perception and rule fusion layer, a mechanism and data-driven joint modeling layer, and a collaborative optimization and fusion decision-making layer, The perception and rule fusion layer is used for collecting water quality parameters, process control parameters and operation state parameters in real time from the pretreatment section, biochemical treatment section, advanced treatment section and sludge treatment section of the sewage plant, preprocessing the data, and fusing an expert rule base. The mechanism and data-driven joint modeling layer is used for establishing a mechanism model and a data-driven model under the constraint condition of the expert rule base, wherein the mechanism model performs process section simulation prediction and outputs a mechanism prediction control quantity, and the data-driven model performs prediction and outputs an AI prediction control quantity. The collaborative optimization and fusion decision-making layer is used for performing multi-objective collaborative optimization and fusion decision-making across process sections based on the output results of the mechanism and data-driven joint modeling layer under the constraint condition of the expert rule base, calculating a dynamic fusion weight and generating a final control quantity, and issuing the final control quantity to an execution device to realize closed-loop optimization through adaptive adjustment combined with real-time feedback.

2. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 1 wherein, The fusion expert rule base comprises converting expert experience and process specifications into a rule parameter set, including the safety threshold range of key control variables of each process section, the logical constraint relationship between variables and the abnormal condition triggering condition, and storing the rule parameter set in the expert rule base for calling by the mechanism model and the data-driven model to provide safety boundary constraint, operation state monitoring and out-of-bound early warning functions during model operation.

3. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 1 wherein, The data preprocessing comprises the following steps: S111, data cleaning, including removing noise, processing missing values and abnormal values; S112, data standardization, including performing zero mean unit variance standardization processing; S113, data time sequencing, including constructing a multi-time step sequence in time order and generating a sliding window sample; S114, data alignment, including interpolating and padding the data of different sampling frequencies and time bases and performing timestamp consistency processing.

4. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 1 wherein, The mechanism model is used for describing and depicting the physical, chemical and biological reaction mechanisms in the sewage treatment process, wherein the mechanism model is constructed based on material balance and kinetic equations and the operation mechanism of each process section, simulates the operation state of each process section in real time, and outputs a mechanism prediction control quantity.

5. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 1 wherein, The data-driven model is used for depicting the nonlinear mapping relationship between input features and target control quantities, wherein the data-driven model is constructed based on historical multivariate time series data, and a deep learning network based on time series prediction structure is used to output an AI prediction control quantity.

6. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 1 wherein, The working process of the collaborative optimization and fusion decision-making layer comprises the following steps: S31, performing multi-objective collaborative optimization across process sections under the constraint condition of the expert rule base; S32, generating a fusion control quantity by dynamically fusing the mechanism prediction control quantity and the AI prediction control quantity; S33: issuing the fusion control quantity for execution, and realizing closed-loop optimization through adaptive adjustment based on feedback.

7. The intelligent decision fusion system for co-ordinated multi-process zone of a wastewater treatment plant as claimed in claim 6 wherein, In step S31, performing multi-objective collaborative optimization across process sections under the constraint condition of the expert rule base comprises: For the water quality compliance rate, energy consumption and reagent dosage, the multi-objective optimization weighted sum method is used to set the weight and objective function for multi-objective optimization, and the optimization objective function is: , Wherein, Z is the total optimization target value; is the weight coefficient of the ith target, satisfying and ; is the ith optimization target function; is the ith control vector; n is the number of optimization targets; The Newton iteration method with constraints is used for the iterative update of the control variables in the collaborative optimization, and the control variable update formula is: , wherein, is the control vector of the dth iteration; is the joint cost function; is the first order gradient vector, i.e. the partial derivative of each control variable with respect to the total objective; is the second order Hessian matrix, i.e. the second order partial derivative; is the adaptive learning rate, dynamically adjusted according to the iteration step size.

8. The intelligent decision fusion system for co-ordinated multi-process zone of wastewater treatment plant as claimed in claim 6 wherein, In step S32, based on the multi-objective system optimization control amount result in S31, the mechanism prediction control amount output by the collaborative optimization is calculated The AI prediction control amount The dynamic fusion weight calculation is carried out, and the dynamic fusion weight adaptive adjustment formula can be expressed as: , Wherein, is a weight adjustment coefficient; is a real-time feedback error, i.e., a weighted sum of deviations of actual values of key indicators of process sections from predicted values; is a maximum error threshold allowed; is an accuracy of AI model prediction control; when , , only is used to ensure safety, and a final control quantity is obtained after dynamic weighted fusion The final control quantity fusion formula is: , wherein, is a dynamic fusion weight, ranging ; is a final issued control amount for execution; is a mechanism prediction control amount output by collaborative optimization; is an AI prediction control amount output by collaborative optimization.

9. The intelligent decision fusion system for co-ordinated multi-process zone of a wastewater treatment plant as claimed in claim 6 wherein, In step S33, the final fusion control quantity obtained in S32 is issued to the corresponding device for execution, and a real-time execution feedback signal is collected And the target set value Calculate the deviation, and realize closed-loop optimization based on adaptive adjustment of the feedback. The feedback deviation calculation formula is:​ , wherein, is a target value; is an actual execution feedback value; is a control deviation at the current time point; The closed-loop optimization is based on the deviation, and the proportional-integral-derivative (PID) is used for closed-loop adjustment, and the calculation formula is: , wherein, is a feedback adjustment signal; is a proportional coefficient, reflecting the strength of the immediate response to the deviation; is an integral coefficient, used to eliminate steady-state error; is a differential coefficient, used to suppress rapid fluctuations in the system; is the rate of change of the deviation, used to predict the trend of the deviation in advance.

10. The intelligent decision fusion system for co-ordinated multi-process zone of a wastewater treatment plant as claimed in claim 9 wherein, On the basis of closed-loop optimization, an adaptive adjustment mechanism is introduced to update the dynamic fusion weight and optimization model parameters according to the feedback error trend, forming a short-term rapid adjustment loop and a long-term strategy optimization loop, and dynamically updating the fusion weight , AI model hyperparameters , and mechanism model sensitivity coefficients to ensure the stability and robustness of control performance under different working conditions, Based on real-time comprehensive error, on a minute to hour level cycle With AI accuracy The fusion weight is dynamically corrected, and a short-term rapid adjustment ring of the fusion weight is realized, and the calculation formula is: , wherein, is a fusion weight for the current moment, with a value range of [0, 1]; is a fusion weight update step, which controls the weight change speed; is a real-time comprehensive error; is a maximum allowed comprehensive error threshold; is an accuracy indicator of the AI model in the recent prediction window, Based on the historical operation data and the feedback evaluation results, the AI model hyperparameters are updated on a daily or weekly basis to achieve long-term strategy optimization of AI model hyperparameters, and the calculation formula is: , wherein, is a hyperparameter of the AI model; m is a long-term optimization iteration step number; is a hyperparameter update learning rate; is a loss function of the AI model; Computing mechanism model parameter correction amount based on feedback data And update the sensitivity coefficient, realize the adaptive correction of the sensitivity coefficient of the mechanism model, and the calculation formula is: , wherein, is a set of sensitivity coefficients of the mechanistic model, including reaction rate constants, conversion efficiency parameters, etc.; is a sensitivity update step size; is a sensitivity correction calculated from the feedback data.

Images