Decision control method and system based on sludge activity health index

Abstract

The invention discloses a decision control method and system based on a sludge activity health index, and relates to the field of sewage treatment, and the method comprises the steps: obtaining data during sewage treatment, respectively calculating a metabolic activity index, a settling performance index, an environmental adaptability index and a treatment efficiency index, carrying out the weighted fusion, obtaining a first sludge activity health index, and obtaining a second sludge activity health index; constructing a sewage treatment model, obtaining a second sludge activity health index, comparing the index data, generating an instruction to the edge server according to a comparison result, and adjusting operation equipment; therefore, the complex biological treatment process state is condensed into a measurable and traceable scalar quantity, so that the beneficial effects of stably reaching the standard, saving energy, reducing consumption and realizing intelligent operation are efficiently achieved.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment, and in particular to a decision control method and system based on the sludge activity and health index. Background Technology

[0002] The activated sludge process is currently the most widely used biological treatment technology in municipal wastewater treatment and industrial wastewater treatment. Its core relies on the microbial community in activated sludge to complete the degradation and transformation of pollutants. Therefore, the health status of activated sludge directly determines the treatment efficiency, effluent stability and operating economy of the wastewater treatment system.

[0003] The wastewater treatment industry faces the dual pressures of "stable and high-standard compliance" and "extreme cost reduction and efficiency improvement." Traditional operating models, relying on manual experience and targeting single parameters (such as fixed dissolved oxygen concentration (DO)), manually setting parameters like blower frequency and chemical dosage, are no longer sufficient. This approach suffers from slow response, coarse control, and poor coordination between units, easily leading to high energy and material consumption, fluctuating effluent quality, and difficulty in handling complex influent changes. Furthermore, PID control based on fixed setpoints cannot detect dynamic changes in influent load and microbial activity, resulting in either "over-aeration" wasting energy or "under-aeration" affecting treatment efficiency. Existing controls often focus on single water quality parameters (such as effluent ammonia nitrogen and total nitrogen) or single process parameters (such as DO), lacking a core indicator that comprehensively reflects the overall "health" status of the activated sludge system.

[0004] To address the aforementioned challenges, the urgent technical problem to be solved in this field is how to provide a decision-making and control method, system, device, and medium that can comprehensively and scientifically reflect the true state of sludge and thus immediately issue coordinated control commands to relevant equipment. Summary of the Invention

[0005] To address the aforementioned technical problems, the purpose of this application is to provide a decision-making and control method and system based on the sludge activity health index (SAHI). This method innovatively defines and calculates in real-time a multi-dimensional integrated comprehensive index: the Sludge Activity Health Index (SAHI). SAHI serves as the sole and unified optimization target for assessing system status and driving all control decisions, thereby sending coordinated control commands to equipment control devices oriented towards the SAHI optimization target. To achieve the above objective, this application provides a decision-making and control method, system, device, and medium based on the sludge activity health index.

[0006] The above-mentioned objective of this application is achieved through the following technical solution: A decision control method based on sludge activity and health index, comprising: Obtain wastewater treatment data; Based on the wastewater treatment data, index calculations are performed, including one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. The results of the index calculation are weighted and fused to obtain the first sludge activity and health index. A wastewater treatment model is constructed based on historical wastewater treatment data. The wastewater treatment data is then input into the wastewater treatment model to obtain the second sludge activity and health index. The first sludge activity health index is compared with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, the cause of the abnormality and suggestions are output from the preset knowledge base, and instructions are generated to adjust the operating equipment according to the suggestions.

[0007] Preferably, the wastewater treatment data includes: Wastewater influent data, biochemical reaction tank data, wastewater effluent data, equipment operation data, and monitoring data.

[0008] Preferably, after acquiring wastewater treatment data, the method further includes: The wastewater treatment data is preprocessed, wherein the preprocessing includes one or more of cleaning, alignment, and standardization.

[0009] Preferably, the metabolic activity index is specifically: The metabolic capacity of sludge microbial communities.

[0010] Preferably, the settlement performance index is: The ability to separate sludge into mud and water.

[0011] Preferably, the environmental adaptability index is specifically: The ability of sludge to resist fluctuations and maintain its internal stability.

[0012] Preferably, the processing efficiency index is specifically: The ability to balance sludge effluent quality with economic benefits.

[0013] Preferably, the preset knowledge base specifically comprises: The system is constructed based on historical data recorded during the sludge treatment process, expert experience rules, and typical operating case studies.

[0014] Preferably, adjusting the operating equipment according to the suggested instructions includes: Based on the suggestions output from the knowledge base, a corresponding wastewater data adjustment instruction is generated and sent to the equipment control device. The equipment control device then generates equipment parameter instructions and sends them to the operating equipment for execution.

[0015] Preferably, after the equipment control device generates the equipment parameter command, it further includes: The device parameter instructions need to be input into the security verification model. After the verification rules of the security verification model are met, they are sent to the running device.

[0016] Preferably, after sending the instruction to the operating device for execution, it further includes: The wastewater treatment data after executing the equipment parameter modification command is obtained, and the calculation of the first sludge activity health index, the wastewater treatment model, and the generation of equipment parameter commands are optimized and upgraded.

[0017] A decision control system based on sludge activity and health index, comprising: The acquisition module is used to acquire wastewater treatment data; The index acquisition module is used to calculate indices based on the wastewater treatment data, wherein the index calculation includes one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. The first index calculation module is used to weight and fuse the results of the index calculation to obtain the first sludge activity and health index. The second index calculation module is used to construct a wastewater treatment model based on historical wastewater treatment data, input the wastewater treatment data into the wastewater treatment model, and obtain the second sludge activity and health index. The comparison module is used to compare the first sludge activity health index with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, the module outputs the cause of the abnormality and suggestions from the preset knowledge base, and generates instructions to adjust the operating equipment according to the suggestions.

[0018] This application uses a newly defined sludge activity health index as an evaluation standard for the operational status of wastewater systems. The calculated sludge activity health index is compared with the theoretical sludge activity health index obtained from a constructed simulated wastewater treatment model to determine the final equipment adjustment process. By condensing the complex biological treatment process into a measurable and traceable scalar, this fundamentally changes the control logic of wastewater treatment, shifting from a passive response to multiple isolated parameters to proactive management and global coordination of a comprehensive health goal. This efficiently solves the key challenges of stable compliance, energy conservation and consumption reduction, and intelligent operation. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a decision control method based on the sludge activity and health index in an embodiment of this application; Figure 2 This is a structural diagram of a decision control system based on the sludge activity and health index in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] Furthermore, the technical features in the various embodiments or individual embodiments provided in this application can be arbitrarily combined with each other to form a feasible technical solution. Such combination is not constrained by the order of steps and / or the structural composition mode, but must be based on the ability of those skilled in the art to implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of units and modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or modules can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical or other forms.

[0024] In addition, each functional unit in the various embodiments of this application can be integrated into a single processor, or each unit can be a separate device, or two or more units can be integrated into a single device; each functional unit in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0025] Those skilled in the art will understand that all or part of the steps of the following method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they perform the steps of the following method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0026] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0027] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" or "several" means two or more, unless otherwise explicitly specified.

[0028] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which this application can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size should still fall within the scope of the technical content disclosed in this application, provided that they do not affect the effects and purposes that this application can produce.

[0029] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0030] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0031] The implementation method of this application is written in a progressive manner.

[0032] like Figure 1 As shown, a decision control method based on the sludge activity and health index includes: S1. Obtain wastewater treatment data; S2. Calculate indices based on wastewater treatment data. The index calculation includes one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. S3. The results of the index calculation are weighted and merged to obtain the first sludge activity and health index; S4. Construct a wastewater treatment model based on historical wastewater treatment data, input wastewater treatment data into the wastewater treatment model, and obtain the second sludge activity and health index. S5. Compare the first sludge activity health index with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, output the cause of the abnormality and suggestions from the preset knowledge base, and generate instructions to adjust the operating equipment according to the suggestions.

[0033] Specifically, all data generated during the wastewater treatment process can be acquired through industrial IoT interfaces; At this point, by using the data obtained from the wastewater treatment process, various indices are calculated. The metabolic activity index, settling performance index, environmental adaptability index, and treatment efficiency index represent various evaluation results in the wastewater treatment process. By weighting and integrating one or more of the above indices, the first sludge activity health index, namely the SAHI value, is finally obtained, which is used to represent the health level of the wastewater treatment system. For example, in one embodiment, the SAHI value calculation process can be represented as follows: SAHI = ω1 * F_metabolism + ω2 * F_sedimentation + ω3 * F_environment + ω4 * F_efficiency; Wherein, ω1, ω2, ω3, and ω4 are dynamic weight coefficients, and their initial values ​​can be set by the domain personnel themselves.

[0034] By constructing a wastewater treatment model, which can be built from historical wastewater treatment data and causal learning, the constructed model can simulate a real wastewater treatment system. Pre-processed data is input into the model to obtain a second sludge activity and health index. The calculated first sludge activity and health index is compared with the second sludge activity and health index. If the first sludge activity and health index is less than the second sludge activity and health index, the abnormality cause and suggestions are output from the preset knowledge base, and instructions are generated to adjust the operating equipment according to the suggestions.

[0035] Since the wastewater treatment model simulates a real-world wastewater treatment system, the obtained data is input into it. The resulting second sludge activity health index is considered the optimal sludge activity health index generated under simulated conditions. Therefore, by using the second sludge activity health index as a threshold, the first sludge activity health index is compared with the second sludge activity health index, and the causes of anomalies and suggestions are output based on a preset knowledge base. If the result of the second sludge activity health index is 0.9, and the calculated result of the first sludge activity health index is 0.8, a diagnosis is triggered. The system analyzes which index involved in the calculation experienced the largest decrease, and by combining this with the preset knowledge base, it outputs specific causes of the decrease and improvement suggestions, generating adjustment instructions.

[0036] Through this diagnostic mechanism, the system can quickly and accurately identify the degree and root cause of the sludge system deviating from the optimal state (such as insufficient metabolic activity, deterioration of settling performance, or excessive energy consumption) through the knowledge base. This triggers regulation with clear pathological indications, realizing the transformation from "passive response to abnormalities" to "active maintenance of health". Ultimately, it ensures that the system continuously approaches the global optimal operating state while maintaining stable compliance with standards, significantly reducing energy and material consumption and improving operational stability.

[0037] In other embodiments, wastewater treatment data includes: Wastewater influent data, biochemical reaction tank data, wastewater effluent data, equipment operation data, and monitoring data.

[0038] Specifically, the wastewater influent data includes: influent flow rate, influent chemical oxygen demand (COD), influent ammonia nitrogen (NH3-N) concentration, and influent total phosphorus (TP) concentration; The data from the biochemical reactor include: dissolved oxygen (DO) concentration, oxidation-reduction potential (ORP), mixed liquor suspended solids (MLSS) concentration, sludge volume index (SVI), temperature, and pH value. Wastewater effluent data include: chemical oxygen demand (COD), ammonia nitrogen (NH3-N) concentration, total nitrogen (TN) concentration, total phosphorus (TP) concentration, and nitrate (NO3-N) concentration.

[0039] Equipment operation data includes: blower operating frequency and current, operating frequency and status of various water pumps (inlet pump, return pump, sludge pump), instantaneous dosage of carbon source addition pump, and dosage of chemical phosphorus removal agent; The monitoring data includes: online respiration rate (OUR) or activated sludge specific oxygen consumption rate (SOUR) data, sludge settling ratio (SV30) data measured manually in the laboratory, and input peak and off-peak electricity price data.

[0040] The data obtained above enables a comprehensive leap from single-parameter monitoring to multi-dimensional health assessment in the generation of sludge health activity index, providing comprehensive, real-time, and accurate data support for the intelligent global optimization of wastewater treatment systems.

[0041] In other embodiments, after acquiring the wastewater treatment data, the method further includes: Wastewater treatment data undergoes data preprocessing, which includes one or more of the following: cleaning, alignment, and standardization.

[0042] Specifically, data cleaning involves removing outliers that are clearly outside the physical range and filling in short-term missing data using linear interpolation or correlation variable estimation methods based on causal graphs.

[0043] Data alignment involves synchronizing data from different sampling periods based on a unified timestamp.

[0044] Data standardization employs the Z-Score method, transforming each variable's data into a distribution with a mean of 0 and a standard deviation of 1 to eliminate the influence of dimensions. The mean (μ) and standard deviation (σ) parameters used are derived from historical data statistics and sent to edge servers and cloud servers.

[0045] By preprocessing the acquired data, the data quality can be significantly improved, providing a more reliable and efficient foundation for subsequent analysis or modeling.

[0046] In other embodiments, the metabolic activity index is specifically: The metabolic capacity of sludge microbial communities.

[0047] The metabolic activity index represents the metabolic capacity of the sludge microbial community. The calculation model is: F_metabolism = f1(X_metabolism). X_metabolism in the model is used as an input feature, including the following data: the online respiration rate (OUR) or specific oxygen consumption rate (SOUR) during the wastewater treatment process, and the rate of decrease in ammonia nitrogen (NH3-N) concentration per unit time. The function f1 can be a pre-trained machine learning model, such as a gradient boosting tree or a shallow neural network model. Historical data is used during training, and the operating conditions with high pollutant removal rate and moderate energy consumption are used as positive labels to learn the mapping relationship between X_metabolism and the score. The closer X_metabolism is to 1, the better the metabolic activity.

[0048] The metabolic activity index characterizes the immediate metabolic capacity of the microbial community in activated sludge, which can intuitively determine the current activity level of microorganisms and provide clear directional guidance for subsequent root cause diagnosis and regulation.

[0049] In some embodiments, the settlement performance index is specifically: The ability to separate sludge into mud and water.

[0050] The settling performance index represents the sludge's ability to separate sludge into sludge and is calculated using the model: F_sedimentation = f2(X_sedimentation). X_sedimentation serves as the input feature in the model and includes the following data: sludge volume index (SVI), mixed liquor suspended solids (MLSS) concentration, and sludge level in the secondary settling tank. The function f2 can be a pre-trained machine learning model. During training, it can be based on SVI grading standards (e.g., SVI < 120 mL / g is excellent, 120-150 mL / g is good, and > 150 mL / g is poor), combined with sludge level stability, allowing the model to output a score for settling performance based on X_sedimentation.

[0051] The settling performance index assesses the sludge-water separation characteristics of activated sludge, providing early warnings of risks such as sludge bulking, sludge loosening, and sludge runoff from the secondary settling tank. This helps prevent abnormal sludge settling from causing excessive levels of suspended solids, total nitrogen, and total phosphorus in the effluent. It also provides a reference for adjusting sludge discharge volume and sludge return ratio.

[0052] In some embodiments, the environmental adaptability index is specifically: The ability of sludge to resist fluctuations and maintain its internal stability.

[0053] The environmental adaptability index represents the sludge's ability to resist fluctuations and maintain internal stability. The calculation model is: F_environment = f3(X_environment). X_sedimentation in the model serves as the input feature, including the following data: the fluctuation variance of the food-to-microbe ratio (F / M, i.e., the amount of organic pollutants that activated sludge can process per unit time) over a past period (e.g., 24 hours); the absolute deviation between the actual sludge age (SRT, i.e., the ratio of the total amount of microorganisms in the system to the amount of microorganisms discharged from the system daily) and the target sludge age SRT; and the real-time fluctuation variance of key parameters (e.g., dissolved oxygen concentration DO, pH). The function f2 can be a pre-trained machine learning model. A high F_environment value indicates that the system has strong buffering capacity and is in a low-risk "sub-healthy" state.

[0054] The environmental adaptability index assesses the sludge system's potential to resist influent fluctuations and maintain inherent operational stability. It can predict in advance whether the system is at risk of operational collapse due to external shocks (such as sudden changes in influent water quality and quantity), supporting the formulation of preventive control strategies. This shifts the focus from passively responding to failures to proactively avoiding risks, significantly improving the system's operational stability.

[0055] In other embodiments, the processing performance index is specifically: The ability to balance sludge effluent quality with economic benefits.

[0056] The treatment efficiency index represents the balance between effluent quality and economic efficiency. The calculation model is as follows: F_efficiency = α * Score_water quality + β * Score_energy consumption + γ * Score_chemical consumption; Among them, Score_water quality is a normalized score calculated based on how close the concentration of each indicator in the current effluent is to its discharge standard limit (the closer to the limit, the lower the score). Score_Energy Consumption is a score that compares the current power consumption per unit of water treated with the historical baseline. Score_Reagent Consumption is a score that compares the carbon source / reagent consumed per unit of pollutant removal to the historical baseline. α, β, γ are configurable weighting coefficients, and α+β+γ=1.

[0057] The treatment efficiency index incorporates the core operational objectives of wastewater treatment (achieving effluent quality standards and reducing costs and increasing efficiency) into the evaluation system. This not only constrains the control strategy to ensure that the effluent quality meets the discharge standards, but also avoids non-economic optimization behaviors such as "excessive aeration and excessive addition of chemicals in pursuit of sludge activity." This ensures that the final control strategy can achieve the overall operational objective of "optimal cost under the premise of meeting standards."

[0058] In other embodiments, a pre-defined knowledge base is specified as follows: The system is constructed based on historical data recorded during the sludge treatment process, expert experience rules, and typical operating case studies.

[0059] Specifically, the pre-set knowledge base can be constructed by acquiring historical data, expert experience rules, typical working condition case libraries, etc., to form a domain knowledge foundation that can support the system in performing state diagnosis, root cause analysis, and control decisions.

[0060] In other embodiments, adjusting the operating device according to the proposed generated instructions includes: Based on the suggestions output from the knowledge base, corresponding wastewater data adjustment instructions are generated and sent to the equipment control device. The equipment control device then generates equipment parameter instructions and sends them to the operating equipment for execution.

[0061] Specifically, wastewater data adjustment instructions are obtained through the output of the knowledge base. These instructions are not specific equipment adjustment settings, but rather wastewater adjustment instructions issued to the equipment control devices. There can be multiple equipment control devices, each controlling different equipment in the wastewater treatment process. Examples include: an aeration intelligent body that dynamically adjusts oxygen supply; a carbon addition intelligent body that precisely adds carbon sources; an internal / external sludge return intelligent body that optimizes sludge return; a sludge discharge intelligent body that controls sludge discharge; and a chemical dosing intelligent body that controls chemical dosing. Each intelligent body possesses a reinforcement learning strategy network or model predictive control (MPC) algorithm, and can autonomously send equipment adjustment instructions based on the received wastewater data adjustment instructions.

[0062] For example: The abnormal cause diagnosed by the knowledge base is: insufficient F_ metabolism, mainly due to low dissolved oxygen (DO) concentration in the aerobic tank; The wastewater data adjustment instruction sent to the aeration intelligent agent controlling the oxygen supply is: "Within the future control period T, increase the target range of the DO dynamic setpoint in aerobic tank A from [1.8, 2.2] mg / L to [2.2, 2.6] mg / L". At the same time, a coordination instruction is sent to the internal recirculation intelligent agent that will be affected: "Adjust the internal recirculation ratio appropriately to match possible changes in nitrification rate". At this time, the aeration intelligent agent and the internal recirculation intelligent agent that receive the instruction send specific equipment control instructions to the control equipment according to the built-in control algorithm.

[0063] When SAHI deviates from its optimal state, the system can immediately pinpoint the specific process dimension causing the "unhealthy" state (e.g., whether it's deteriorated sedimentation performance or insufficient metabolic activity), thus achieving a leap from "monitoring abnormalities" to "diagnosing the root cause." This makes subsequent regulatory instructions no longer blind or empirical, but rather "targeted therapy" with a clear pathological orientation, significantly improving the accuracy and response efficiency of regulation.

[0064] By constructing a hierarchical decision-making architecture of "SAHI value diagnosis - knowledge base reasoning - intelligent agent execution", the scientific decomposition and professional collaboration of process control tasks are realized. The decision center of the upper-level SAHI focuses on system-level health diagnosis and macro-control intent generation. It can output adjustment instructions oriented towards process goals without delving into the details of equipment control, which greatly reduces the complexity of cross-level decision-making. The intelligent agents of each process unit in the lower level, with the help of reinforcement learning policy networks or MPC algorithms, accurately transform macro-instructions into optimal execution parameters adapted to the characteristics of their respective equipment. This not only ensures the professionalism and accuracy of control actions, but also endows the system with strong adaptive capabilities. It can autonomously optimize the execution strategy according to the real-time operating conditions, and finally realize "distributed intelligent execution driven by global optimal goal", which significantly improves the response speed, control accuracy and operational robustness of the sewage treatment system.

[0065] In some embodiments, after the device control device generates the device parameter instruction, it further includes: The device parameter commands must be input into the security verification model. After the security verification model's verification rules are met, they are then sent to the running device.

[0066] Specifically, at this point, the generated device parameter instructions also need to be verified through a preset security verification model. Only instructions that pass all security verifications can be issued and executed. Instructions that fail will be intercepted and an alarm will be triggered. At the same time, correction suggestions will be returned for the device control device to make a new decision to avoid generating instructions that do not conform to the operation of the device.

[0067] By running safety rules for verification, abnormal instructions that may exceed equipment safety limits, violate process allowable ranges, or cause cascading failures are effectively intercepted and corrected. This ensures that even if the AI ​​policy network produces extreme outputs during the exploration and learning process, it will not endanger equipment safety and process stability, thereby achieving an organic unity between improving the efficiency and ensuring the operational safety of the wastewater treatment system.

[0068] In other embodiments, after being sent to the operating device for instruction execution, the method further includes: The wastewater treatment data obtained after executing the equipment parameter modification command is optimized and upgraded, and the calculation of the first sludge activity and health index, the wastewater treatment model, and the generation of equipment parameter commands are optimized and upgraded.

[0069] Specifically, after the operating equipment executes instructions, process data from the start of wastewater influent to the end of operation is collected, thus recording and saving all data on the complete chain to form a trajectory sample. At this time, the edge server can fine-tune the weight coefficients (ω1~ω4) in the SAHI calculation model based on recent data to make it more in line with the current actual working conditions; it can also be used to optimize the (f1, f2, f3) calculation model in the SAHI calculation model to improve the evaluation accuracy; and it is also used to train the predictive control algorithm in the control devices of various equipment. By adopting a multi-agent reinforcement learning framework, the design core of the reward function is strongly correlated with SAHI. For example: Total reward function = R_SAHI improvement + R_cost savings - R_excess penalty, where R_SAHI improvement is directly proportional to the positive change in SAHI value, R_cost savings are directly proportional to the reduction in energy and chemical consumption, and R_excess penalty provides a large negative reward when the effluent water quality exceeds the standard. Through training, the equipment control device learns how to coordinate its actions to maximize the long-term cumulative reward, that is, to achieve a joint improvement in SAHI and economic benefits.

[0070] The wastewater treatment model can also be updated and optimized based on recent operational data to make it more consistent with real-world operating conditions, thereby improving the accuracy of the theoretical sludge health index, i.e., the second sludge health index, and making the assessment results more accurate.

[0071] like Figure 2 As shown, a decision control system based on the sludge activity and health index includes: Module 101 is used to acquire wastewater treatment data; The index acquisition module 102 is used to calculate indices based on wastewater treatment data. The index calculation includes one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. The first index calculation module 103 is used to weight and fuse the results of the index calculation to obtain the first sludge activity and health index. The second index calculation module 104 is used to construct a wastewater treatment model based on historical wastewater treatment data, input wastewater treatment data into the wastewater treatment model, and obtain the second sludge activity and health index. The comparison module 105 is used to compare the first sludge activity health index with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, the abnormality cause and suggestions are output from the preset knowledge base, and instructions are generated to adjust the operating equipment according to the suggestions.

[0072] This application uses a newly defined sludge activity health index as an evaluation standard for the operational status of wastewater systems. The calculated sludge activity health index is compared with the theoretical sludge activity health index obtained from a constructed simulated wastewater treatment model to determine the final equipment adjustment process. This fundamentally changes the control logic of wastewater treatment, shifting from a passive response to multiple isolated parameters to proactive management and global coordination of a comprehensive health goal. This efficiently achieves the beneficial effects of stable compliance, energy saving and consumption reduction, and intelligent operation.

[0073] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0074] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0075] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A decision control method based on sludge activity and health index, characterized in that, include: Obtain wastewater treatment data; Based on the wastewater treatment data, index calculations are performed, including one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. The results of the index calculation are weighted and fused to obtain the first sludge activity and health index. A wastewater treatment model is constructed based on historical wastewater treatment data. The wastewater treatment data is then input into the wastewater treatment model to obtain the second sludge activity and health index. The first sludge activity health index is compared with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, the cause of the abnormality and suggestions are output from the preset knowledge base, and instructions are generated to adjust the operating equipment according to the suggestions.

2. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The wastewater treatment data includes: Wastewater influent data, biochemical reaction tank data, wastewater effluent data, equipment operation data, and monitoring data.

3. The decision control method based on sludge activity and health index according to claim 1, characterized in that, After acquiring wastewater treatment data, the following is also included: The wastewater treatment data is preprocessed, wherein the preprocessing includes one or more of cleaning, alignment, and standardization.

4. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The metabolic activity index is specifically: The metabolic capacity of sludge microbial communities.

5. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The settlement performance index is specifically as follows: The ability to separate sludge into mud and water.

6. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The environmental adaptability index is specifically: The ability of sludge to resist fluctuations and maintain its internal stability.

7. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The processing efficiency index is specifically: The ability to balance sludge effluent quality with economic benefits.

8. The decision control method based on sludge activity and health index according to claim 1, characterized in that, The preset knowledge base is specifically as follows: The system is constructed based on historical data recorded during the sludge treatment process, expert experience rules, and typical operating case studies.

9. The decision control method based on sludge activity and health index according to claim 1, characterized in that, Based on the recommendations, instructions are generated to adjust the operating equipment, including: Based on the suggestions output from the knowledge base, a corresponding wastewater data adjustment instruction is generated and sent to the equipment control device. The equipment control device then generates equipment parameter instructions and sends them to the operating equipment for execution.

10. The decision control method based on sludge activity and health index according to claim 9, characterized in that, After the equipment control device generates equipment parameter instructions, it also includes: The device parameter instructions need to be input into the security verification model. After the verification rules of the security verification model are met, they are sent to the running device.

11. The decision control method based on sludge activity and health index according to claim 9, characterized in that, After the instructions are sent to the running device for execution, the following are also included: The wastewater treatment data after executing the equipment parameter modification command is obtained, and the calculation of the first sludge activity health index, the wastewater treatment model, and the generation of equipment parameter commands are optimized and upgraded.

12. A decision control system based on sludge activity and health index, characterized in that, include: The acquisition module is used to acquire wastewater treatment data; The index acquisition module is used to calculate indices based on the wastewater treatment data, wherein the index calculation includes one or more of the following: metabolic activity index, sedimentation performance index, environmental adaptability index, and treatment efficiency index. The first index calculation module is used to weight and fuse the results of the index calculation to obtain the first sludge activity and health index. The second index calculation module is used to construct a wastewater treatment model based on historical wastewater treatment data, input the wastewater treatment data into the wastewater treatment model, and obtain the second sludge activity and health index. The comparison module is used to compare the first sludge activity health index with the second sludge activity health index. If the first sludge activity health index is less than the second sludge activity health index, the module outputs the cause of the abnormality and suggestions from the preset knowledge base, and generates instructions to adjust the operating equipment according to the suggestions.

Images