A general model intelligent control method and system for sewage treatment engineering based on ASM

Abstract

The present invention relates to the field of sewage engineering control technology, and in particular to an intelligent control method and system for a universal sewage treatment engineering model based on ASM. By integrating the ASM model with the sludge growth dynamics model, the present invention constructs a universal sewage treatment engineering model that combines physical mechanism drive with data drive, overcoming the problem of insufficient applicability of traditional models. The model is not only process-universal but also dynamically adaptable to specific sewage plant operating conditions, significantly enhancing the model's versatility and scenario adaptability. Through the error monitoring and parameter correction feedback module, closed-loop adaptive optimization of the universal sewage treatment engineering model is achieved, overcoming the problem that traditional static models cannot self-correct according to real-time operation deviations. The model's prediction accuracy and control effect can be continuously improved, ensuring stable and efficient operation of the system under complex dynamic conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage engineering control, and in particular to an intelligent control method and system for a sewage treatment engineering universal model based on ASM. Background Art

[0002] Currently, process control for biological wastewater treatment processes in sewage treatment plants primarily relies on a series of control strategies based on activated sludge models (ASMs). These models, typically ASM1, ASM2, and ASM3, were proposed by the International Water Association (IWA). They describe the removal of pollutants (such as COD, ammonia nitrogen, nitrate, total nitrogen, and total phosphorus) by microbial communities through mathematical equations, describing biochemical reaction mechanisms such as bacterial growth, substrate consumption, nitrification, denitrification, and phosphorus release. Existing control methods typically involve offline process optimization based on ASM simulation results during sewage treatment plant design or renovation, or by combining traditional PID control with empirical rule-based threshold control to adjust process parameters such as aeration rate, sludge return ratio, and carbon source addition to achieve effluent quality and energy savings.

[0003] However, the problem with existing technologies is that the ASM model is essentially a simplified model developed for teaching and theoretical research. Its default parameters (such as maximum specific growth rate, half-saturation constant, oxygen limitation coefficient, etc.) are based on idealized experimental conditions and have large deviations from the actual operating conditions of specific sewage treatment plants (including influent water quality fluctuations, temperature changes, sludge age fluctuations, etc.). As a result, the model requires a large amount of parameter calibration and adjustment in engineering applications. Secondly, existing solutions often use the ASM model as a static prediction tool, lacking the ability to link with real-time data and unable to adaptively adjust to nonlinear, time-varying, and perturbation characteristics in the process. Thirdly, traditional control methods (such as PID control) have a delayed response to complex coupled biochemical processes and insufficient adjustment accuracy, making it difficult to cope with sudden load shocks or multi-objective optimization needs (such as denitrification, phosphorus removal, and energy conservation). Summary of the Invention

[0004] The present invention proposes an intelligent control method and system for a universal model of sewage treatment engineering based on ASM. The aim is to integrate the ASM model with the sludge growth dynamics model, introduce a nonlinear compensation algorithm and operating parameter correction, and construct a universal control method and control system based on the ASM model suitable for sewage treatment engineering, thereby realizing multi-source control of sewage treatment engineering.

[0005] Among them, a sewage treatment engineering general model intelligent control method based on ASM includes the following steps:

[0006] S1. Obtain multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and construct a multi-source operating data matrix related to the sewage treatment plant;

[0007] S2. Based on the multi-source operating condition data matrix, the reaction rate functions and state variable sets corresponding to the multi-source operating condition data matrix in the ASM model and the sludge growth kinetics model are extracted through state variable mapping. A universal sewage treatment engineering model is constructed, and a state prediction matrix is ​​output based on the multi-source operating condition data.

[0008] S3. Based on the state prediction matrix, a weighted multi-objective control model is constructed, and the sewage treatment control quantity sequence is output through the rolling horizon model predictive control;

[0009] S4. Based on the sewage treatment control quantity sequence, the sewage treatment system is controlled in real time to obtain and collect actual operating condition response data, construct an actual operating condition response data matrix, and calculate a prediction error matrix based on the state prediction matrix;

[0010] S5. According to the prediction error matrix, the parameters of the universal sewage treatment engineering model are corrected, the parameter correction matrix is ​​output and the process returns to step S3 to perform closed-loop control on the universal sewage treatment engineering model.

[0011] An intelligent control system for a sewage treatment engineering universal model based on ASM, which is implemented based on any one of the above-mentioned intelligent control methods for a sewage treatment engineering universal model based on ASM, and is characterized by comprising:

[0012] Multi-source data acquisition module, used to collect multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and build a multi-source operating data matrix related to the sewage treatment plant;

[0013] The engineering model construction and state prediction module is used to extract the reaction rate function and state variable set corresponding to the multi-source operating condition data matrix in the ASM model and sludge growth kinetics model through state variable mapping based on the multi-source operating condition data matrix, construct a universal sewage treatment engineering model, and output a state prediction matrix based on the multi-source operating condition data;

[0014] The control strategy generation module is used to construct a weighted multi-objective control model based on the state prediction matrix and output the sewage treatment control quantity sequence through the rolling horizon model prediction control;

[0015] The control strategy error monitoring module is used to control the sewage treatment system in real time according to the sewage treatment control quantity sequence, obtain the actual working condition response data, construct the actual working condition response data matrix, and calculate the prediction error matrix based on the state prediction matrix;

[0016] The parameter correction and feedback module is used to correct the parameters of the universal sewage treatment engineering model according to the prediction error matrix, and output the parameter correction matrix to perform closed-loop control on the universal sewage treatment engineering model.

[0017] A computer-readable storage medium for storing a computer program, which, when run on a computer, enables the computer to execute an ASM-based general model intelligent control method for sewage treatment engineering as described in any one of the above.

[0018] An electronic device, comprising:

[0019] Memory, used to store computer programs;

[0020] A processor is used to execute the computer program to implement an ASM-based sewage treatment engineering general model intelligent control method as described in any of the above items.

[0021] The beneficial effects of the present invention are:

[0022] (1) The present invention deeply integrates the ASM model with the sludge growth dynamics model to construct a universal sewage treatment engineering model that combines physical mechanism drive with data drive. This overcomes the problem of insufficient applicability of traditional models caused by single reliance on empirical formulas or single data fitting, making the model both process universal and able to dynamically adapt to specific sewage plant operating conditions, significantly enhancing the model's versatility and scenario adaptability.

[0023] (2) The present invention establishes a high-quality and highly consistent data input system through a hierarchical data preprocessing process including multi-source data collection, missing value repair, outlier removal, and nonlinear normalization, providing solid data support for model fusion and effectively avoiding prediction bias introduced by multi-source data spuriousness, noise, and anomalies, thus laying a reliable foundation for subsequent prediction and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of an intelligent control method for a general model of sewage treatment engineering based on ASM proposed by the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0026] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention is further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention and are not intended to limit the present invention. That is, the embodiments described herein are only some embodiments of the present invention, not all embodiments. Generally, the components of the embodiments of the present invention described and illustrated in the drawings herein may be arranged and designed in various different configurations.

[0027] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative work shall fall within the scope of protection of the present invention. It should be noted that relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0028] Furthermore, the terms "comprises," "comprising," or any other variations thereof are intended to cover a non-exclusive inclusion such that a process, method, article, or machine that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, method, article, or machine. In the absence of more limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article, or machine that comprises the element.

[0029] The features and performance of the present invention are further described in detail below with reference to the embodiments.

[0030] Example 1

[0031] like Figure 1 As shown, the embodiment of the present invention provides an intelligent control method for a sewage treatment engineering universal model based on ASM, comprising the following steps:

[0032] S1. Obtain multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and construct a multi-source operating data matrix related to the sewage treatment plant;

[0033] S2. Based on the multi-source operating condition data matrix, the reaction rate functions and state variable sets corresponding to the multi-source operating condition data matrix in the ASM model and the sludge growth kinetics model are extracted through state variable mapping. A universal sewage treatment engineering model is constructed, and a state prediction matrix is ​​output based on the multi-source operating condition data.

[0034] S3. Based on the state prediction matrix, a weighted multi-objective control model is constructed, and the sewage treatment control quantity sequence is output through the rolling horizon model predictive control;

[0035] S4. Based on the sewage treatment control quantity sequence, the sewage treatment system is controlled in real time to obtain and collect actual operating condition response data, construct an actual operating condition response data matrix, and calculate a prediction error matrix based on the state prediction matrix;

[0036] S5. According to the prediction error matrix, the parameters of the universal sewage treatment engineering model are corrected, the parameter correction matrix is ​​output and the process returns to step S3 to perform closed-loop control on the universal sewage treatment engineering model.

[0037] Furthermore, step S1 specifically includes the following sub-steps:

[0038] S101. Collect data from the sewage treatment plant, including influent pollutant concentration, effluent pollutant concentration, aeration rate, sludge age (SRT), reflow ratio, pH value, and water temperature, and construct an original data matrix based on the collected data;

[0039] S102. Extract spectral features by constructing a local linear trend model within the time window, retaining the boundary observations unchanged, performing linear weighted calculations using the known data points on the left and right, and interpolating the boundaries of missing values ​​in the original data matrix;

[0040] S103. By setting a sliding time window of fixed length, the original data of different sampling frequencies are aggregated within the window, and a multi-source working condition data matrix with consistent time steps is uniformly output.

[0041] Specifically, the implementation principle flow of each sub-step in the above embodiment is as follows:

[0042] In step S101, through multi-source data collection, with the same sampling time length and variable dimension, the sewage treatment plant's operating data including influent water quality (COD, NH4⁺, TN, etc.), effluent indicators, aeration volume, reflow ratio, sludge concentration (MLSS), temperature, pH, etc. are collected to construct a multi-source operating data matrix. To ensure the consistency of data sources, the same sampling time length must be used, and the variable dimensions of each working condition data must be consistent. For example, data is collected from the SCADA system of the sewage treatment plant, and combined with online water quality monitoring instruments with unified data format standards and templated manual experimental record history records, a multi-source working condition data matrix of the sewage treatment plant is constructed. .

[0043] In step S102, the missing items in the multi-source operating condition data matrix and the sampling frequency differences of different data sources are normalized. By using the boundary-preserving linear interpolation repair theory, the missing values ​​in the multi-source data matrix are repaired, which is expressed as: ,in Indicates at a point in time Missing values ​​obtained by interpolation, 、 Indicates the time points corresponding to the left and right ends of the missing value. 、 The left and right ends of the missing value correspond to the known values ​​at the time point. The sliding window is used to resample the multi-source working condition data with inconsistent sampling periods, which can be expressed as: ,in represents the resampled mean of variable i within the window period, represents the sliding window length, Represents the observed value of variable i at time point k. The multi-source operating condition data matrix with interpolation, repair and sampling alignment is obtained.

[0044] In step S103, the sliding Z-score anomaly detection method is used to identify outliers in the multi-source operating condition data matrix that is interpolated, repaired, and sampled. The data mean and standard deviation are calculated respectively. The outliers in the multi-source operating condition data are extracted and replaced based on the Z-score anomaly detection method to obtain a multi-source operating condition data matrix with a unified output time step.

[0045] Furthermore, the step S2 specifically includes the following sub-steps:

[0046] S201. Extracting the organic matter degradation and sludge growth rate calculation submodel and the ASM model state variable set from the ASM model based on the multi-source operating condition data matrix. Also extracting the environmental modulation function and the sludge dynamics model state variable set from the sludge dynamics model based on the multi-source operating condition data matrix. By unifying the saturated substrate concentration term and the dissolved oxygen regulation function, the organic matter degradation and sludge growth rate calculation submodel and the environmental modulation function are functionally integrated to construct a total rate calculation model that includes a dual regulation mechanism.

[0047] S202. Introduce environmental impact adjustment factors to adaptively compensate the total rate calculation model and dynamically adjust the biochemical reaction intensity;

[0048] S203. Extracting and constructing a variable interchange mapping matrix based on the spectral characteristics of the multi-source working condition data matrix, the ASM model state variable set and the sludge dynamics model state variable set are merged through the variable interchange mapping matrix to construct a unified state description space;

[0049] S204. Through the error feedback back propagation mechanism, the acquisition error term is used to adaptively learn the unified state description space to obtain a universal sewage treatment engineering model, and a state prediction matrix is ​​output based on multi-source operating condition data.

[0050] Specifically, the implementation principle of each sub-step in the above embodiment is as follows:

[0051] In step S201, first, the ASM model reaction rate formula is extracted based on the multi-source operating condition data matrix: ,in represents the maximum specific growth rate of heterotrophic bacteria, represents the soluble matrix (BOD) concentration at time t, represents the half-saturated substrate constant, represents the dissolved oxygen concentration at time t, represents the oxygen half-saturation constant, Represents the heterotrophic biomass concentration; extract the ASM model state variable set: ,in, represents the concentration of soluble matrix, represents the concentration of heterotrophic bacteria, represents the concentration of autotrophic nitrifying bacteria, Indicates the concentration of polyphosphate bacteria, represents the nitrate nitrogen concentration. Then the environmental regulation function in the sludge growth kinetics model is extracted: ,in represents the theoretical maximum specific growth rate of sludge, Represents the environmental sensitive factor function; extracts the state variable set of the sludge dynamics model: ,in, Indicates the concentration of suspended solids in the mixed liquid. Indicates the concentration of volatile suspended solids in the mixed liquid, Indicates the sludge age, Represents the food to microbial load ratio.

[0052] Specifically, the Activated Sludge Model (ASM), proposed by the International Water Association (IWA), is a classic mathematical description system for the activated sludge process. It originated from the ASM1 model, launched by the IWA (then known as the IAWPRC) in 1987, and subsequently expanded into the ASM2, ASM2d, and ASM3 series. The ASM model is primarily based on long-term operational data from wastewater treatment plants. Its core concept is to describe the behavior of microbial communities in mixed liquor suspended solids (MLSS) using a set of metabolic reactions (including organic matter degradation, nitrogen and phosphorus conversion, nitrification, and denitrification) and related biokinetic rate equations. Construction of this model requires the definition of a series of basic parameters, such as dissolved biodegradable organic matter concentration, particulate organic matter concentration, dissolved oxygen concentration, ammonia nitrogen concentration, nitrite and nitrate concentrations, active heterotrophic bacteria concentration, active autotrophic bacteria concentration, and endogenous residual concentration, as well as corresponding kinetic parameters (such as the maximum specific growth rate μmax, the half-saturation constant Ks, the endogenous respiration coefficient bH, the ammonia oxidation rate μA, and the denitrification rate μD). The core mechanism of the ASM model is to divide the material flow and energy flow in the sewage treatment process into a series of components, and perform coupled simulation through mass conservation, rate equations, and stoichiometric relationships, which can comprehensively characterize complex biological reaction processes.

[0053] Sludge kinetic growth models are primarily derived from classic Monod dynamics, bioreactor theory, and sludge retention time (SRT) control theory. By defining microbial growth rate, decay rate, endogenous respiration, and substrate consumption dynamics, these models describe the temporal evolution of sludge volume, active components, and biomass. Model construction typically requires the collection of parameters such as sludge concentration (MLSS, MLVSS), influent and effluent substrate concentrations (such as COD, BOD, and ammonia nitrogen), sludge yield coefficient (Y), maximum specific growth rate (μmax), half-saturation constant (Ks), endogenous respiration coefficient (b), and sludge settling properties (such as SVI). By substituting these parameters into the Monod equation and mass balance equation, dynamic sludge growth and decay equations can be established, enabling the prediction and regulation of microbial population size and activity levels in bioreactors. This model is not only used to predict the treatment capacity of the activated sludge system, but is also often used as an important tool for sewage treatment process optimization, aeration control, residual sludge production prediction and energy consumption analysis. When combined with the ASM model, it can realize the comprehensive coupling analysis of substrate, microorganism and environment in the engineering model.

[0054] In step S202, the environmental impact adjustment factor is introduced , adaptive compensation is performed on the total rate calculation model. The environmental sensitive factor function is used to combine temperature regulation, dissolved oxygen regulation and sludge regulation terms, and is embedded in the total rate calculation model as a scaling regulator of the biochemical rate. In step S203, the ASM model state variable set and the sludge dynamics model state variable set are constructed according to the ASM model and the sludge growth dynamics model respectively, and variable exchange mapping is performed. According to the mapping relationship, the two sets are constructed into a unified state description space. In step S204, through the error feedback back propagation mechanism, the unified state description space is adaptively learned using the collected error terms to obtain a universal sewage treatment engineering model, and a state prediction matrix is ​​output based on multi-source operating condition data.

[0055] Specifically, the specific implementation principle process of step S204 is as follows:

[0056] First, based on the unified state description space, the state variable set of the ASM model is The state variable parameters obtained after fusion with the sludge dynamics model state variable set are collected according to the control cycle of the sewage treatment plant. At the beginning of each control cycle (such as every 30 minutes), the latest operating data of the sewage treatment plant corresponding to the state variable parameters are collected through multi-source data collection. , combined with the actual operating response data in the previous control cycle , based on the generalized sewage treatment engineering model of the current control cycle version, a forward propagation is performed to obtain the state prediction value within the current control cycle ; According to the state prediction value within the control cycle at the current time t The actual working condition response data of the control cycle at the current time t By comparison, the prediction error value of the current control cycle is calculated, which is expressed as ,in Indicates the prediction error value within the control period at the current time t.

[0057] Then, based on the prediction error value, the error loss function is constructed ,in represents the state variable parameters in the unified state description space, Indicates the The weight factor of the state variable parameter, Indicates the The prediction error value of the state variable parameter in the current control cycle; through the backpropagation mechanism, about Calculate the gradient and use an optimization algorithm (such as the Adam algorithm or the L-BFGS algorithm) to perform gradient updates to obtain the updated state variable parameters .

[0058] Then, according to the updated state variable parameters, the unified state description space, the total rate calculation model and the error loss function are combined to obtain the universal sewage treatment engineering model. The state variable parameters of the universal sewage treatment engineering model are updated and the state prediction matrix of the next control cycle is output. .

[0059] Finally, according to the state prediction matrix of the next control cycle , serving as the data input for step S3, provides accurate state prior predictions for generating the sewage treatment control quantity sequence. This enables error-driven adaptive model construction, self-optimizing prediction, and a closed-loop feedback mechanism. The system possesses excellent generalization capabilities, rapid adaptability to unexpected operating conditions, and stability and convergence in long-term operation.

[0060] Furthermore, the total rate calculation model is specifically expressed as: in, represents the actual biological reaction rate at time t, represents the maximum specific growth rate, represents the concentration of soluble matrix, represents the half-saturated substrate constant, represents the dissolved oxygen concentration at time t, represents the oxygen half-saturation constant, Represents the environmental sensitivity factor function.

[0061] Furthermore, in step S203, the unified state description space is specifically expressed as:

[0062] ;

[0063] in, represents the target variable vector, represents the variable mapping matrix, Represents the state variable set of the ASM model, Represents the set of state variables of the sludge dynamics model.

[0064] Specifically, the variable mapping matrix The construction principle is as follows:

[0065] First, based on the multi-source working condition data matrix , perform time series spectrum analysis and obtain the ASM model state variable set and the state variable set of the sludge dynamics model The response frequency bands and collaborative features between the two state variable sets are determined by mutual information analysis and principal component correlation sorting to determine the high correlation mapping channel between the two state variable sets; then, the ASM model state variable set and the state variable set of the sludge dynamics model The physical meaning and time series coupling behavior of the state variables are used to construct an initial variable interchange rule table. The physical meaning refers to the state variables in the two state variable sets being variables that reflect organic matter concentration, biomass, or oxygen concentration. Logical mapping and unit conversion factors are used to construct a set of candidate mapping function families, including at least linear mapping functions, exponential mapping functions, and piecewise mapping functions. Then, by minimizing the state prediction error criterion, a quasi-Newton gradient optimization algorithm is used to train and calibrate the parameters in these function families, and finally converge to obtain the optimal variable mapping structure, that is, to form the variable mapping matrix. ; The variable mapping matrix Essentially, it is a weighted association matrix whose element values ​​represent the set of state variables of the ASM model. and the state variable set of the sludge dynamics model In the , the mapping intensity or proportion of a state variable to the target uniform variable. Finally, the variable mapping matrix As the basic structure of variable mapping, the ASM model state variable set is mapped during the model fusion operation. and the state variable set of the sludge dynamics model Linear combination and transformation are performed to construct a unified state description space, achieving structural consistency and state controllability of the ASM model and the sludge dynamics model.

[0066] By introducing a dual rate control mechanism, multiple factors such as heterotrophic biomass concentration, soluble substrate concentration, dissolved oxygen concentration and maximum specific growth rate of heterotrophic bacteria are integrated into the rate calculation model, and the state set is unified through the variable mapping matrix. This can carefully characterize the complex multiphase reaction mechanism and overcome the technical bottleneck that a single model is difficult to capture the inherent multivariable coupling relationship of the system.

[0067] Furthermore, the step S3 specifically includes the following sub-steps:

[0068] S301. Based on the state prediction matrix, a weighted multi-objective control model is constructed with the goals of minimizing effluent pollution concentration, minimizing operating energy consumption, and balancing sludge load stability;

[0069] S302. Set the initial variable sequence, take the initial variable sequence as the minimum feasible solution space, adopt the rolling horizon model predictive control, and calculate the optimal control variable sequence in each control cycle as the sewage treatment control quantity sequence.

[0070] Furthermore, in step S301, the weighted multi-objective control model is constructed with the goals of minimizing the effluent pollution concentration, minimizing the operating energy consumption, and balancing the sludge load stability, including the following sub-steps:

[0071] S3011. With the goal of minimizing the effluent pollution concentration, calculate the time-accumulated value of the L2 norm error between the predicted effluent pollutant value and the target emission value, specifically expressed as:

[0072] ;

[0073] in, Indicates the penalty item for pollutant emissions deviating from the target, represents the predicted water pollutant concentration vector at time t, represents the target effluent discharge standard concentration vector, represents the Euclidean norm squared;

[0074] S3012. With the goal of minimizing operating energy consumption, calculate the cumulative power consumption of the aeration equipment and the sludge pump, specifically expressed as:

[0075] ;

[0076] in, Indicates the penalty item for operating energy consumption deviating from the target, represents the power consumption of the aeration equipment at time t, represents the power consumption of the sludge pump at time t;

[0077] S3013. Taking the sludge load stability balance as the goal, calculate the approach value between the unit sludge load and the sewage treatment plant design load target, specifically expressed as:

[0078] ;

[0079] in, represents the penalty term for sludge load stability deviation from the target, represents the suspended solids concentration of the mixed solution at time t, represents the average sludge residence time at time t, represents the target ratio;

[0080] S3014. Based on the calculated time accumulated value, power consumption accumulated value and approach value, a weighted multi-objective control model is constructed, which is specifically expressed as follows:

[0081] ;

[0082] in, represents the weighted multi-objective control model, 、 、 The contributions of effluent pollution concentration, operating energy consumption, and sludge load stability to the weighted multi-objective control model are shown, respectively. This weighted multi-objective control model ensures effluent quality while minimizing energy consumption and stabilizing system loads. This overcomes the shortcomings of traditional control methods, which focus on a single objective and lack comprehensive trade-offs, and provides a multi-objective collaborative optimization solution for wastewater treatment processes.

[0083] Furthermore, the step S4 specifically includes the following sub-steps:

[0084] S401. According to the sewage treatment control quantity sequence, the multi-source operating data are controlled in real time, and the actual operating response data are collected in real time according to the fixed sampling interval to construct the actual operating response data matrix;

[0085] S402. Using timestamp matching and variational dynamic time warping algorithms, align the actual operating condition response data matrix with the state prediction matrix, and calculate the prediction error matrix.

[0086] Furthermore, the step S5 specifically includes the following sub-steps:

[0087] S501. Perform sensitivity analysis on the parameters of the weighted multi-objective control model based on the prediction error matrix, and obtain a priority update parameter subset by calculating the partial derivatives of the error matrix and the corresponding parameters;

[0088] S502. Based on the priority update parameter subset, a multi-scale coordination factor is introduced, and the parameters of the priority update parameter subset are updated in combination with the model complexity constraint;

[0089] S503. Output a parameter correction matrix based on the updated priority update parameter subset, and feed the parameter correction matrix back to step S3.

[0090] Furthermore, the step S501 specifically includes the following sub-steps:

[0091] S5011. According to the prediction error matrix, calculate the norm of the current prediction error matrix;

[0092] S5012. Calculate the sensitivity partial derivatives of all parameters in the weighted multi-objective control model based on the prediction error matrix norm;

[0093] S5013. Set a sensitivity threshold based on the historical multi-source operating data of the sewage treatment plant, and sort the sensitivity partial derivatives of all parameters. When the sensitivity partial derivative is higher than the sensitivity threshold, it is regarded as a high-sensitivity parameter and the priority update parameter subset is obtained.

[0094] Furthermore, step S502 specifically includes the following sub-steps:

[0095] S5021. Set the basic learning rate according to the dynamic learning strategy;

[0096] S5022. Perform spectral decomposition on the prediction error matrix and calculate the frequency error components and normalized energy weights of all parameters in the prediction error matrix respectively;

[0097] S5023. According to the priority update parameter subset, calculate the correction amount of each parameter in the subset under the frequency error component, and combine the correction amount of each parameter into the final update amount.

[0098] Through error monitoring and parameter correction feedback, closed-loop adaptive optimization of the universal sewage treatment engineering model is achieved, overcoming the problem that traditional static models cannot self-correct according to real-time operation deviations. It can continuously improve the model's prediction accuracy and control effect, ensuring the stable and efficient operation of the system under complex dynamic conditions.

[0099] Example 2

[0100] As a preferred implementation of the above embodiment, an intelligent control system of a sewage treatment engineering universal model based on ASM is proposed. The system is implemented based on any of the above-mentioned intelligent control methods of the sewage treatment engineering universal model based on ASM, and includes:

[0101] Multi-source data acquisition module, used to collect multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and build a multi-source operating data matrix related to the sewage treatment plant;

[0102] The engineering model construction and state prediction module is used to extract the reaction rate function and state variable set corresponding to the multi-source operating condition data matrix in the ASM model and sludge growth kinetics model through state variable mapping based on the multi-source operating condition data matrix, construct a universal sewage treatment engineering model, and output a state prediction matrix based on the multi-source operating condition data;

[0103] The control strategy generation module is used to construct a weighted multi-objective control model based on the state prediction matrix and output the sewage treatment control quantity sequence through the rolling horizon model prediction control;

[0104] The control strategy error monitoring module is used to control the sewage treatment system in real time according to the sewage treatment control quantity sequence, obtain the actual working condition response data, construct the actual working condition response data matrix, and calculate the prediction error matrix based on the state prediction matrix;

[0105] The parameter correction and feedback module is used to correct the parameters of the universal sewage treatment engineering model according to the prediction error matrix, and output the parameter correction matrix to perform closed-loop control on the universal sewage treatment engineering model.

[0106] Furthermore, the multi-source operating condition data include inlet pollutant concentration, outlet pollutant concentration, aeration volume, sludge age SRT, recirculation ratio, pH value and water temperature.

[0107] Furthermore, the engineering model construction and state prediction module specifically includes:

[0108] A dual-regulation rate model construction module is used to extract the organic matter degradation and sludge growth rate calculation submodel and the ASM model state variable set from the ASM model based on the multi-source operating condition data matrix. It also extracts the environmental modulation function and the sludge dynamics model state variable set from the sludge dynamics model based on the multi-source operating condition data matrix. By unifying the saturated substrate concentration term and the dissolved oxygen regulation function, the organic matter degradation and sludge growth rate calculation submodel and the environmental modulation function are functionally integrated to construct a total rate calculation model that includes a dual-regulation mechanism.

[0109] Environmental factor adjustment module, used to introduce environmental impact adjustment factors, perform adaptive compensation on the total rate calculation model, and dynamically adjust the biochemical reaction intensity;

[0110] The variable fusion mapping module extracts and constructs a variable interchange mapping matrix based on the spectral characteristics of the multi-source working condition data matrix. The state variable set of the ASM model and the state variable set of the sludge dynamics model are fused through the variable interchange mapping matrix to construct a unified state description space.

[0111] The model solving and state response module is used to adaptively learn the unified state description space using the collected error terms through the error feedback back propagation mechanism, obtain a universal sewage treatment engineering model, and output a state prediction matrix based on multi-source operating condition data.

[0112] Furthermore, the control strategy generation module specifically includes:

[0113] The multi-objective fusion constraint integration module is used to construct a weighted multi-objective control model based on the state prediction matrix, with the goals of minimizing effluent pollution concentration, minimizing operating energy consumption, and balancing sludge load stability;

[0114] The control sequence generation module is used to set the initial variable sequence, take the initial variable sequence as the minimum feasible solution space, adopt the rolling horizon model predictive control, and calculate the optimal control variable sequence in each control cycle as the sewage treatment control quantity sequence.

[0115] Specifically, the implementation principle process of the above system is as follows:

[0116] First, the multi-source data acquisition module collects multi-source operating condition data, including influent pollutant concentration, effluent pollutant concentration, aeration rate, sludge age (SRT), recirculation ratio, pH value, and water temperature, from multiple sources, including the sewage treatment plant's SCADA system, online water quality monitoring instruments, and manual testing platforms. Through preprocessing such as missing value repair, time alignment, outlier removal, and normalization, a multi-source operating condition data matrix is ​​constructed to adapt to the model input. This data matrix serves as the core input for the subsequent engineering modeling and prediction modules.

[0117] Subsequently, the dual-regulation rate model construction module extracts the organic matter degradation rate and sludge growth rate formulas from the ASM model. The environmental modulation function is introduced from the sludge dynamics model. By unifying the saturated substrate concentration term and the dissolved oxygen modulation function, the rate calculation model is integrated to form an overall rate calculation function that represents carbon and nitrogen removal and sludge dynamics. Furthermore, the environmental factor adjustment module introduces environmental modulation factors, including temperature and pH, to adaptively compensate the overall rate model and dynamically adjust the biochemical reaction intensity. Then, by analyzing the spectral characteristics of the multi-source operating condition data matrix, a state variable interchange mapping matrix is ​​constructed. The state variable set of the ASM model is uniformly mapped to the state variable set of the sludge dynamics model to establish a unified state description space. Furthermore, an error feedback backpropagation mechanism is incorporated to adaptively learn the unified state space using error terms collected under actual operating conditions. This results in a universal sewage treatment engineering model. A state prediction matrix is ​​then output in real time based on multi-source data, forming a prediction of future treatment states.

[0118] During control, the state prediction matrix is ​​used as input. First, a weighted multi-objective control model is constructed through the multi-objective fusion constraint integration module, focusing on the multi-objective control requirements of minimizing effluent pollution concentration, minimizing operating energy consumption, and stabilizing sludge load. Next, the control sequence generation module sets the initial variable sequence as the minimum feasible solution space. Using the rolling horizon model predictive control (MPC) strategy, the optimal control variable sequence (such as aeration rate, recirculation ratio, and sludge discharge) is calculated in real time within each control cycle. This output is used as the sewage treatment control variable sequence to drive the engineering control of the sewage treatment plant.

[0119] After control is implemented, the multi-source data acquisition module collects real-time operating response parameters such as actual effluent indicators, energy consumption levels, and sludge concentration based on the real-time operating response after the sewage treatment control quantity sequence is controlled. This data matrix is ​​constructed and compared with the state prediction matrix to calculate the prediction error matrix. Using the prediction error matrix, an error backpropagation mechanism is used to correct sensitive parameters in the universal sewage treatment engineering model (such as reaction rate constants, adjustment factors, and saturation coefficients). The parameter correction matrix is ​​then output, achieving closed-loop optimization of the entire modeling and control chain.

[0120] Example 3

[0121] Based on the first embodiment, there is a multi-objective control application scenario of a sewage treatment plant, which adopts the intelligent control method and system of the sewage treatment engineering general model based on ASM described in the above embodiment.

[0122] Its specific implementation method is:

[0123] In practical applications, this embodiment uses a large-scale sewage treatment plant in a certain city as a test scenario, employing an ASM-based sewage treatment engineering general model intelligent control method and system implementation to achieve multi-objective optimization control for effluent water quality compliance, energy consumption reduction, and sludge load stability. The sewage treatment plant's SCADA system, online water quality monitoring instruments, and artificial experimental platform collect multi-source operating data in real time, including influent COD, NH4⁺, TN, TP concentrations, effluent indicators, aeration rate, sludge age (SRT), reflow ratio, sludge concentration (MLSS), pH value, and water temperature, to construct a matrix of raw operating data. Through missing value repair, sliding window resampling, sliding Z-score outlier removal, and nonlinear piecewise normalization, the system-preprocessed data matrix is ​​standardized and encapsulated as the input to the fusion model.

[0124] During the engineering model construction and state prediction process, the system uses a dual-rate control model construction module to integrate the organic matter degradation and nitrification and denitrification rate formulas of the ASM model with the environmental modulation function of the sludge dynamics model at a functional level to form a total rate calculation model. The environmental factor adjustment module also introduces dynamic temperature and pH adjustment factors to enhance the model's adaptability to different climatic conditions and influent shocks. The variable fusion mapping module utilizes the spectral characteristics of multi-source operating data to establish a variable interchange mapping relationship between the ASM and sludge models, forming a state prediction matrix containing various state variables in a unified state description space. Through the model solution and state response module, the system uses historical and real-time operating data for adaptive iterative learning based on an error feedback backpropagation mechanism to predict future trends in effluent COD, NH4⁺, TN, and other indicators in real time.

[0125] Based on the state prediction matrix, the control strategy generation module constructs a weighted multi-objective control model with the goals of minimizing effluent pollution concentration, minimizing total aeration energy consumption, and minimizing sludge load fluctuations. It sets the initial control variable sequence (such as initial aeration volume, recirculation ratio, sludge discharge volume, etc.) and uses the rolling horizon model predictive control (MPC) algorithm to calculate the optimal control variable sequence within each control cycle and output it to the sewage treatment plant's actuators for real-time adjustment. The control strategy error monitoring module, based on the actual operating condition response of sewage treatment, collects effluent indicators, energy consumption, and sludge concentration, constructs a data matrix of actual operating condition response, compares it with the predicted value, and calculates the prediction error matrix. Based on this, the parameter correction and feedback module corrects the reaction rate constant, adjustment factor, and other parameters of the universal sewage treatment engineering model to achieve full-link closed-loop control.

[0126] The experimental test period lasted for 30 consecutive days. Results showed that after implementing this intelligent control system, the average effluent COD value dropped from 35 mg / L to 28 mg / L, the average NH⁺ value dropped from 2.5 mg / L to 1.8 mg / L, and the average TN value dropped from 13 mg / L to 10.5 mg / L, increasing the effluent compliance rate from 92% to 98%. Aeration system energy consumption was reduced by approximately 12.3% compared to the original empirical control strategy, and sludge load fluctuation (measured by the MLSS standard deviation) decreased by approximately 18.7%. The system demonstrated enhanced adaptability and stability under complex operating conditions such as peak loads, low temperatures, and inlet surges. Through dynamic error closed-loop adjustment, the model prediction error converged from an initial average of 12% to within 5% in long-term operation, significantly improving the multi-objective integrated control capabilities and system operational efficiency of the wastewater treatment process.

[0127] Example 4

[0128] Based on the first embodiment, this embodiment proposes a terminal device for intelligent control of a sewage treatment engineering universal model based on ASM. The terminal device includes at least one memory, at least one processor, and a bus connecting different platform systems.

[0129] The memory may include readable media in the form of volatile memory, such as RAM 211 and / or cache memory, and may further include ROM 213 .

[0130] The memory also stores a computer program that can be executed by the processor, so that the processor executes any of the above-mentioned ASM-based sewage treatment engineering general model intelligent control methods in the embodiments of the present application. Its specific implementation method is consistent with the implementation method and the technical effect achieved in the embodiments of the above-mentioned method, and some of the contents are not repeated here. The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data. Each of these examples or some combination may include the implementation of a network environment.

[0131] Accordingly, the processor may execute the aforementioned computer program, as well as the program / utility.

[0132] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0133] The terminal device can also communicate with one or more external devices such as keyboards, pointing devices, Bluetooth devices, etc., and can also communicate with one or more devices that can interact with the terminal device, and / or communicate with any device (such as a router, a modem, etc.) that enables the terminal device to communicate with one or more other computing devices. This communication can be carried out through an I / O interface. In addition, the terminal device can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter. The network adapter can communicate with other modules of the terminal device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the terminal device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0134] Example 5

[0135] Building on Example 1, this example proposes a computer-readable storage medium for intelligent control of a universal model for wastewater treatment engineering based on ASM. The computer-readable storage medium stores instructions that, when executed by a processor, implement any of the aforementioned methods for intelligent control of a universal model for wastewater treatment engineering based on ASM. The specific implementation methods and technical effects achieved are consistent with those described in the examples of the aforementioned methods, and some details are omitted here.

[0136] The present embodiment provides a program product for implementing the above method, which can adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In the present embodiment, the readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0137] A computer-readable storage medium may include a data signal transmitted in baseband or as part of a carrier wave, carrying readable program code. This transmitted data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which can transmit, transmit, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof. The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a standalone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet via an Internet service provider).

[0138] The foregoing description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein and should not be construed as excluding other embodiments. Rather, the present invention can be used in various other combinations, modifications, and environments and can be modified within the scope of the concept described herein through the above teachings or techniques or knowledge in the relevant field. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention are intended to be protected by the appended claims.

Claims

1. A general model intelligent control method for sewage treatment engineering based on ASM, characterized by: The following steps are involved: S1. Obtain multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and construct a multi-source operating data matrix related to the sewage treatment plant; S2. Based on the multi-source operating condition data matrix, the reaction rate functions and state variable sets corresponding to the multi-source operating condition data matrix in the ASM model and the sludge growth kinetics model are extracted through state variable mapping. A universal sewage treatment engineering model is constructed, and a state prediction matrix is ​​output based on the multi-source operating condition data. S3. Based on the state prediction matrix, a weighted multi-objective control model is constructed, and the sewage treatment control quantity sequence is output through the rolling horizon model predictive control; S4. Based on the sewage treatment control quantity sequence, the sewage treatment system is controlled in real time to obtain and collect actual operating condition response data, construct an actual operating condition response data matrix, and calculate a prediction error matrix based on the state prediction matrix; S5. According to the prediction error matrix, the universal sewage treatment engineering model parameters are corrected, the parameter correction matrix is ​​output and returns to step S3, the universal sewage treatment engineering model closed-loop control; The multi-source operating condition data is preprocessed, including extracting spectral features by constructing a local linear trend model within a time window, retaining boundary observation values ​​unchanged, performing linear weighted calculations using left and right known data points, interpolating and repairing the boundaries of missing values ​​in the original data matrix, and performing in-window mean aggregation on the original data of different sampling frequencies by setting a sliding time window of fixed length, and uniformly outputting a multi-source operating condition data matrix with consistent time steps; The step S2 comprises the following steps: S201. Extracting the organic matter degradation and sludge growth rate calculation submodel and the ASM model state variable set from the ASM model based on the multi-source operating condition data matrix. Also extracting the environmental modulation function and the sludge dynamics model state variable set from the sludge dynamics model based on the multi-source operating condition data matrix. By unifying the saturated substrate concentration term and the dissolved oxygen regulation function, the organic matter degradation and sludge growth rate calculation submodel and the environmental modulation function are functionally integrated to construct a total rate calculation model that includes a dual regulation mechanism. S202. Introduce environmental impact adjustment factors to adaptively compensate the total rate calculation model and dynamically adjust the biochemical reaction intensity; S203. Extract and construct a variable interchange mapping matrix based on the spectral characteristics of the multi-source operating condition data matrix, fuse the ASM model state variable set and the sludge dynamics model state variable set through the variable interchange mapping matrix, and construct a unified state description space.

2. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: The multi-source operating data of the sewage treatment plant are obtained, including collecting inlet pollutant concentration, effluent pollutant concentration, aeration volume, sludge age SRT, reflow ratio, pH value and water temperature from the sewage treatment plant to construct an original data matrix.

3. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: Step S2 includes: Through the error feedback back propagation mechanism, the acquisition error term is used to adaptively learn the unified state description space to obtain a universal sewage treatment engineering model, and the state prediction matrix is ​​output based on multi-source operating data.

4. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: In step S201, the total rate calculation model is specifically expressed as: ； in, represents the actual biological reaction rate at time t, represents the maximum specific growth rate, represents the soluble matrix concentration at time t, represents the half-saturated substrate constant, represents the dissolved oxygen concentration at time t, represents the oxygen half-saturation constant, Represents the environmental sensitivity factor function.

5. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: In step S203, the unified state description space is specifically represented as: ； in, represents the target variable vector, represents the variable mapping matrix, Represents the state variable set of the ASM model, Represents the set of state variables of the sludge dynamics model.

6. The ASM-based sewage treatment engineering general model intelligent control method according to claim 1 is characterized in that: Step S3 includes the following steps: S301. Based on the state prediction matrix, a weighted multi-objective control model is constructed with the goals of minimizing effluent pollution concentration, minimizing operating energy consumption, and balancing sludge load stability; S302. Set the initial variable sequence, take the initial variable sequence as the minimum feasible solution space, adopt the rolling horizon model predictive control, and calculate the optimal control variable sequence in each control cycle as the sewage treatment control quantity sequence.

7. The ASM-based sewage treatment engineering general model intelligent control method according to claim 6 is characterized in that: In step S301, a weighted multi-objective control model is constructed with the goals of minimizing effluent pollution concentration, minimizing operating energy consumption, and balancing sludge load stability, including the following sub-steps: S3011. With the goal of minimizing the effluent pollution concentration, calculate the time-accumulated value of the L2 norm error between the predicted effluent pollutant value and the target emission value, specifically expressed as: ； in, Indicates the penalty item for pollutant emissions deviating from the target, represents the predicted water pollutant concentration vector at time t, represents the target effluent discharge standard concentration vector, represents the Euclidean norm squared; S3012. With the goal of minimizing operating energy consumption, calculate the cumulative power consumption of the aeration equipment and the sludge pump, specifically expressed as: ； in, Indicates the penalty item for operating energy consumption deviating from the target, represents the power consumption of the aeration equipment at time t, represents the power consumption of the sludge pump at time t; S3013. Taking the sludge load stability balance as the goal, calculate the approach value between the unit sludge load and the sewage treatment plant design load target, specifically expressed as: ； in, represents the penalty term for sludge load stability deviation from the target, represents the suspended solids concentration of the mixed solution at time t, represents the average sludge residence time at time t, represents the target ratio; S3014. Based on the calculated time accumulated value, power consumption accumulated value and approach value, a weighted multi-objective control model is constructed, which is specifically expressed as follows: ； in, represents the weighted multi-objective control model, 、 、 They respectively represent the contribution of water pollution concentration to the weighted multi-objective control model, the contribution of operating energy consumption to the weighted multi-objective control model, and the contribution of sludge load stability to the weighted multi-objective control model.

8. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: Step S4 includes the following steps: S401. According to the sewage treatment control quantity sequence, the multi-source operating data are controlled in real time, and the actual operating response data are collected in real time according to the fixed sampling interval to construct the actual operating response data matrix; S402. Using timestamp matching and variational dynamic time warping algorithms, align the actual operating condition response data matrix with the state prediction matrix, and calculate the prediction error matrix.

9. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 1 is characterized in that: Step S5 includes the following steps: S501. Perform sensitivity analysis on the parameters of the weighted multi-objective control model based on the prediction error matrix, and obtain a priority update parameter subset by calculating the partial derivatives of the error matrix and the corresponding parameters; S502. Based on the priority update parameter subset, a multi-scale coordination factor is introduced, and the parameters of the priority update parameter subset are updated in combination with the model complexity constraint; S503. Output a parameter correction matrix based on the updated priority update parameter subset, and feed the parameter correction matrix back to step S3.

10. The ASM-based sewage treatment engineering general model intelligent control method according to claim 9, characterized in that: The step S501 includes the following sub-steps: S5011. According to the prediction error matrix, calculate the norm of the current prediction error matrix; S5012. Calculate the sensitivity partial derivatives of all parameters in the weighted multi-objective control model based on the prediction error matrix norm; S5013. Set a sensitivity threshold based on the historical multi-source operating data of the sewage treatment plant, and sort the sensitivity partial derivatives of all parameters. When the sensitivity partial derivative is higher than the sensitivity threshold, it is regarded as a high-sensitivity parameter and the priority update parameter subset is obtained.

11. The intelligent control method of sewage treatment engineering general model based on ASM according to claim 9, characterized in that: The step S502 includes the following sub-steps: S5021. Set the basic learning rate according to the dynamic learning strategy; S5022. Perform spectral decomposition on the prediction error matrix and calculate the frequency error components and normalized energy weights of all parameters in the prediction error matrix respectively; S5023. According to the priority update parameter subset, calculate the correction amount of each parameter in the subset under the frequency error component, and combine the correction amount of each parameter into the final update amount.

12. An intelligent control system for a sewage treatment engineering universal model based on ASM, which is implemented based on an intelligent control method for a sewage treatment engineering universal model based on ASM according to any one of claims 1 to 11, and is characterized in that: include: Multi-source data acquisition module, used to collect multi-source operating data of the sewage treatment plant, pre-process the multi-source operating data, and build a multi-source operating data matrix related to the sewage treatment plant; The engineering model construction and state prediction module is used to extract the reaction rate function and state variable set corresponding to the multi-source operating condition data matrix in the ASM model and sludge growth kinetics model through state variable mapping based on the multi-source operating condition data matrix, construct a universal sewage treatment engineering model, and output a state prediction matrix based on the multi-source operating condition data; The control strategy generation module is used to construct a weighted multi-objective control model based on the state prediction matrix and output the sewage treatment control quantity sequence through the rolling horizon model prediction control; The control strategy error monitoring module is used to control the sewage treatment system in real time according to the sewage treatment control quantity sequence, obtain the actual working condition response data, construct the actual working condition response data matrix, and calculate the prediction error matrix based on the state prediction matrix; The parameter correction and feedback module is used to correct the parameters of the universal sewage treatment engineering model according to the prediction error matrix, and output the parameter correction matrix to perform closed-loop control on the universal sewage treatment engineering model.

13. The ASM-based sewage treatment engineering general model intelligent control system according to claim 12, characterized in that: The multi-source operating condition data include inlet pollutant concentration, outlet pollutant concentration, aeration volume, sludge age SRT, recirculation ratio, pH value and water temperature.

14. The ASM-based sewage treatment engineering general model intelligent control system according to claim 12, characterized in that: The engineering model construction and state prediction module specifically includes: A dual-regulation rate model construction module is used to extract the organic matter degradation and sludge growth rate calculation submodel and the ASM model state variable set from the ASM model based on the multi-source operating condition data matrix. It also extracts the environmental modulation function and the sludge dynamics model state variable set from the sludge dynamics model based on the multi-source operating condition data matrix. By unifying the saturated substrate concentration term and the dissolved oxygen regulation function, the organic matter degradation and sludge growth rate calculation submodel and the environmental modulation function are functionally integrated to construct a total rate calculation model that includes a dual-regulation mechanism. Environmental factor adjustment module, used to introduce environmental impact adjustment factors, perform adaptive compensation on the total rate calculation model, and dynamically adjust the biochemical reaction intensity; The variable fusion mapping module is used to extract and construct a variable interchange mapping matrix based on the spectral characteristics of the multi-source working condition data matrix, and fuse the ASM model state variable set with the sludge dynamics model state variable set through the variable interchange mapping matrix to construct a unified state description space; The model solving and state response module is used to adaptively learn the unified state description space using the collected error terms through the error feedback back propagation mechanism, obtain a universal sewage treatment engineering model, and output a state prediction matrix based on multi-source operating condition data.

15. The ASM-based sewage treatment engineering general model intelligent control system according to claim 12, characterized in that: The control strategy generation module specifically includes: The multi-objective fusion constraint integration module is used to construct a weighted multi-objective control model based on the state prediction matrix, with the goals of minimizing effluent pollution concentration, minimizing operating energy consumption, and balancing sludge load stability; The control sequence generation module is used to set the initial variable sequence, take the initial variable sequence as the minimum feasible solution space, adopt the rolling horizon model predictive control, and calculate the optimal control variable sequence in each control cycle as the sewage treatment control quantity sequence.

Images