Real-time detection method and system for sewage treatment effluent quality

Abstract

The present invention relates to the technical field of sewage treatment, and in particular to a real-time detection method and system for sewage treatment effluent water quality. The method is applied to a sewage treatment system, and the method comprises: dividing the discharge path of the sewage treatment system into at least two effluent monitoring nodes, and presetting a weight rule library of water quality characteristic parameters for each effluent monitoring node; collecting in real time a water quality characteristic parameter set of each effluent monitoring node, an operating status data set of the sewage treatment system, and an environmental parameter data set; determining the current operating condition of the sewage treatment system based on the operating status data, and matching the corresponding parameter weight configuration in the weight rule library; performing weight analysis on the water quality characteristic parameter data and the parameter weight configuration to generate a comprehensive water quality anomaly index corresponding to the effluent monitoring node; accurately tracing the abnormal process location of the sewage treatment and improving the accuracy of anomaly positioning.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a method and system for real-time detection of sewage treatment effluent quality. Background Art

[0002] With the acceleration of industrialization and rising urbanization, wastewater treatment has become a crucial component of environmental protection. The operational effectiveness of wastewater treatment systems is directly related to the quality and ecological safety of the water environment. Existing water quality monitoring technologies often rely on fixed terminal detection devices. These typically use a single sensor at the discharge outlet, such as an online chemical oxygen demand analyzer or an ammonia nitrogen probe. These sensors periodically sample water quality parameters and use them to determine if the water is acceptable.

[0003] However, due to the differences in water quality change characteristics in different process sections of the treatment process, a single monitoring point cannot trace the location of abnormal sewage treatment processes, making it difficult to locate abnormalities; at the same time, existing methods do not fully consider the differences in the degree of influence of various water quality characteristic parameters on water quality under different operating conditions of the sewage treatment system; for example, when the sewage treatment plant load is high and the treatment process is complex, the importance of certain water quality parameters may change significantly, and the existing methods cannot adaptively adjust the weights, making the water quality assessment results inaccurate.

[0004] Therefore, there is an urgent need for a real-time detection method for sewage treatment effluent quality that can comprehensively monitor the discharge path, accurately analyze water quality characteristic parameters, make full use of multi-source data, and timely and accurately locate abnormal links in sewage treatment. Summary of the Invention

[0005] The present invention provides a method and system for real-time detection of sewage treatment effluent quality, which can accurately trace the abnormal process location of sewage treatment and improve the accuracy of abnormal positioning, and can effectively solve the problems in the background technology.

[0006] In order to achieve the above objectives, in a first aspect, the present invention provides a method for real-time detection of water quality of sewage treatment effluent, the method being applied to a sewage treatment system, the method comprising:

[0007] Divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes, and preset a weight rule library of water quality characteristic parameters for each of the effluent monitoring nodes;

[0008] Real-time collection of the water quality characteristic parameter set of each outlet monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set;

[0009] Determine the current operating condition of the sewage treatment system based on the operating status data, and match the corresponding parameter weight configuration in the weight rule library based on the current operating condition of the sewage treatment system;

[0010] Performing weight analysis on the water quality characteristic parameter data and the parameter weight configuration to generate a comprehensive water quality anomaly index corresponding to the outlet water monitoring node;

[0011] Inputting the environmental parameter data and the operating status data into a preset environmental compensation model, outputting an environmental compensation coefficient, and compensating and correcting the comprehensive water quality abnormality index based on the coefficient to obtain a corrected abnormality index;

[0012] Compare the corrected abnormal index with the preset water quality threshold:

[0013] If the corrected abnormality index exceeds the threshold, an over-standard warning is triggered and the abnormal water discharge monitoring node is located; otherwise, the data collection and abnormality index calculation steps are continuously executed.

[0014] In combination with the first aspect, in one possible design, the weight rule library includes parameter weight configurations corresponding to different operating conditions, and the operating conditions include treated water volume range, influent water quality category and equipment load level.

[0015] In combination with the first aspect, in one possible design, the water quality characteristic parameter set includes at least any two of pH value, turbidity, dissolved oxygen concentration, ammonia nitrogen concentration, and total phosphorus concentration;

[0016] The operating status data set includes at least the current treated water volume and equipment operating parameters;

[0017] The environmental parameter data set includes at least environmental temperature, environmental humidity and environmental pressure.

[0018] In combination with the first aspect, in a possible design, the calculation formula of the comprehensive water quality abnormality index is: ;in, represents the comprehensive abnormal water quality index corresponding to the j-th outlet monitoring node, represents the real-time collected value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node; represents the standard limit of the i-th water quality characteristic parameter corresponding to the j-th outlet monitoring node; It represents the weight value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node. The weight value is obtained from the weight rule library according to the current operating conditions. n represents the total number of characteristic parameters in the water quality characteristic parameter set corresponding to the j-th outlet water monitoring node. k represents the nonlinear dynamic index factor, which is used to enhance the sensitivity of the exceeding parameters.

[0019] In combination with the first aspect, in a possible design, the calculation formula of the nonlinear dynamic exponential factor k is: ;

[0020] By setting the nonlinear dynamic index factor, when the ratio of the real-time collected value of the water quality characteristic parameter to the standard limit is ≥1.2, k=1.5 is used, otherwise k=1.2 is used.

[0021] In combination with the first aspect, in a possible design, the calculation formula of the environmental compensation model is: ;

[0022] in, Represents the energy change caused by temperature change; Indicates real-time temperature; Indicates the reference temperature; represents the temperature sensitivity coefficient;

[0023] Represents the energy change caused by humidity change; Indicates real-time humidity; Represents the humidity sensitivity coefficient;

[0024] It represents the energy change caused by pressure change; Indicates real-time pressure; Indicates standard pressure; Indicates the pressure sensitivity coefficient; Indicates the dissolved oxygen activation flag, with a value of 0 or 1, indicating whether compensation is enabled;

[0025] Indicates the energy change caused by the change of sewage treatment flow; Indicates real-time sewage treatment flow; Indicates the maximum flow rate; Indicates rated flow; It represents the flow sensitivity coefficient;

[0026] Indicates the energy change caused by the equipment load level; Indicates the real-time equipment load level, such as the aerator power percentage; Indicates the equipment load level sensitivity coefficient;

[0027] represents the environmental compensation coefficient; 、 、 、 and Represents the normalized functions of temperature, humidity, pressure, sewage treatment flow and equipment load level respectively.

[0028] In conjunction with the first aspect, in one possible design, the weight rule library for presetting the water quality characteristic parameters for each outlet water monitoring node includes:

[0029] Based on the historical operation data of the sewage treatment system, analyze the water quality change characteristics of different treatment process sections and determine the influence weight of each water quality characteristic parameter on water quality under different working conditions;

[0030] According to the influence weight, a weight rule library is constructed using a machine learning algorithm, and the machine learning algorithm includes at least one of a support vector machine, a random forest, or a gradient boosting tree.

[0031] In conjunction with the first aspect, in one possible design, the real-time collection of the water quality characteristic parameter set of each outlet monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set includes:

[0032] A distributed sensor network is used to deploy multiple types of sensors at each of the outlet water monitoring nodes, wherein the sensors include at least two of optical sensors, electrochemical sensors, and microbial sensors;

[0033] By interacting with the sewage treatment system's automatic control system and environmental monitoring system, the system can obtain real-time operating status data and environmental parameter data, and perform real-time verification and cleaning on the collected data to remove outliers and noise data.

[0034] In combination with the first aspect, in one possible design, determining the current operating condition of the sewage treatment system based on the operating status data, and matching the corresponding parameter weight configuration in the weight rule library based on this, includes:

[0035] Perform feature extraction and feature engineering on the operating status data to construct a feature vector reflecting the operating status of the sewage treatment system;

[0036] Using a clustering algorithm to divide the feature vectors into different operating condition categories, the clustering algorithm includes at least one of K-Means clustering, DBSCAN clustering, and Gaussian mixture model clustering;

[0037] According to the current operating condition category, the corresponding parameter weight configuration is matched in the weight rule library.

[0038] In a second aspect, the present invention further provides a real-time detection system for sewage treatment effluent quality, comprising:

[0039] A monitoring node module is used to divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes and preset a weight rule library of water quality characteristic parameters for each effluent monitoring node;

[0040] The data acquisition module is used to collect the water quality characteristic parameter set of each effluent monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set in real time;

[0041] An operating condition analysis module, configured to determine a current operating condition based on the operating status data of the sewage treatment system, and to match corresponding parameter weight configurations in the weight rule library based on the current operating condition;

[0042] The abnormal index calculation module is used to perform weighted calculation on the water quality characteristic parameter data and the matching parameter weight configuration to generate the comprehensive water quality abnormal index corresponding to each outlet monitoring node;

[0043] The compensation module is used to input the environmental parameter data and the operating status data into a preset environmental compensation model, output the environmental compensation coefficient, and compensate and correct the comprehensive water quality abnormality index according to the environmental compensation coefficient to obtain the corrected abnormality index;

[0044] The alarm module is used to compare the corrected abnormal index with the preset water quality threshold; if the corrected abnormal index exceeds the water quality threshold, an over-standard warning is triggered and the abnormal water outlet monitoring node is located; otherwise, the data collection and abnormal index calculation steps are continuously executed.

[0045] The technical solution of the present invention can achieve the following technical effects: by dividing the discharge path into multiple effluent monitoring nodes, the limitations of the previous single monitoring point are overcome, and comprehensive coverage of the discharge path of the sewage treatment system is achieved; each node can collect a set of water quality characteristic parameters in real time. When water quality is abnormal, the abnormal effluent monitoring node can be quickly located based on the data of each node, and the abnormal process location of the sewage treatment can be accurately traced, thereby improving the accuracy of abnormal location and overcoming the difficulty of traditional methods in identifying the abnormal link.

[0046] A weighted rule library for water quality characteristic parameters is preset for each effluent monitoring node. The current operating condition is determined based on the operating status data of the sewage treatment system, and the corresponding parameter weight configuration is then matched. This fully considers the differences in the degree to which various water quality characteristic parameters affect water quality under different operating conditions. Under different operating conditions such as high sewage treatment plant load and complex treatment processes, the weights can be adaptively adjusted to make the water quality assessment results more in line with the actual situation. Compared with traditional fixed weight assessment methods, the accuracy of water quality assessment is improved.

[0047] The operating status data set and environmental parameter data set of the sewage treatment system are collected in real time and combined with the water quality characteristic parameter data; the operating status data reflects the internal working conditions of the system, and the environmental parameter data reflects the impact of the external environment on the water quality; through the preset environmental compensation model, these multi-source data are used to output the environmental compensation coefficient to compensate and correct the comprehensive water quality anomaly index to obtain the corrected anomaly index. By comprehensively considering multiple factors affecting water quality, the one-sidedness of a single data source is avoided, thereby optimizing the water quality anomaly assessment system, making the final anomaly assessment result more comprehensive and reliable, and being able to more timely and accurately judge whether the water quality meets the standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a logic flow chart of the real-time detection method for sewage treatment effluent quality in the present invention;

[0050] Figure 2 This is a structural block diagram of the real-time detection system for sewage treatment effluent quality in the present invention. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0052] The present application is described below in conjunction with the accompanying drawings.

[0053] like Figure 1 As shown, the real-time detection method of sewage treatment effluent quality of the present invention is applied to a sewage treatment system and specifically comprises the following steps:

[0054] Step S1: Divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes, and preset a weight rule library of water quality characteristic parameters for each effluent monitoring node; the weight rule library contains parameter weight configurations corresponding to different operating conditions, wherein the operating conditions include the treated water volume range, the influent water quality category, and the equipment load level;

[0055] Step S2: real-time collection of a water quality characteristic parameter set of each outlet monitoring node, an operating status data set of the sewage treatment system, and an environmental parameter data set; the water quality characteristic parameter set includes at least any two of pH value, turbidity, dissolved oxygen concentration, ammonia nitrogen concentration, and total phosphorus concentration; the operating status data set includes at least the current treated water volume and equipment operating parameters; and the environmental parameter data set includes at least ambient temperature, ambient humidity, and ambient air pressure;

[0056] Step S3: determining the current operating condition of the sewage treatment system according to the operating status data, and matching the corresponding parameter weight configuration in the weight rule library;

[0057] Step S4: performing weight analysis on the water quality characteristic parameter data and the parameter weight configuration to generate a comprehensive water quality anomaly index corresponding to the outlet water monitoring node;

[0058] Step S5: inputting the environmental parameter data and the operating status data into a preset environmental compensation model, outputting an environmental compensation coefficient, and compensating and correcting the comprehensive water quality abnormality index based on the coefficient to obtain a corrected abnormality index;

[0059] Step S6: compare the corrected abnormal index with the preset water quality threshold value: if the corrected abnormal index exceeds the threshold value, trigger an over-standard warning and locate the abnormal water outlet monitoring node; otherwise, continue to execute the data collection and abnormal index calculation steps.

[0060] In this embodiment, the discharge path is divided into multiple effluent monitoring nodes, overcoming the limitations of a single monitoring point in the past and achieving comprehensive coverage of the sewage treatment system's discharge path. Each node can collect a set of water quality characteristic parameters in real time. When water quality anomalies occur, the abnormal effluent monitoring node can be quickly located based on the data from each node, accurately tracing the abnormal process location in the sewage treatment process. This improves the accuracy of anomaly location and overcomes the difficulty of traditional methods in identifying the abnormal link.

[0061] A weighted rule library for water quality characteristic parameters is preset for each effluent monitoring node. The current operating condition is determined based on the operating status data of the sewage treatment system, and the corresponding parameter weight configuration is then matched. This fully considers the differences in the degree to which various water quality characteristic parameters affect water quality under different operating conditions. Under different operating conditions such as high sewage treatment plant load and complex treatment processes, the weights can be adaptively adjusted to make the water quality assessment results more in line with the actual situation. Compared with traditional fixed weight assessment methods, the accuracy of water quality assessment is greatly improved.

[0062] The operating status data set and environmental parameter data set of the sewage treatment system are collected in real time and combined with the water quality characteristic parameter data; the operating status data reflects the internal working conditions of the system, and the environmental parameter data reflects the impact of the external environment on the water quality; through the preset environmental compensation model, these multi-source data are used to output the environmental compensation coefficient to compensate and correct the comprehensive water quality anomaly index to obtain the corrected anomaly index. By comprehensively considering multiple factors affecting water quality, the one-sidedness of a single data source is avoided, thereby optimizing the water quality anomaly assessment system, making the final anomaly assessment result more comprehensive and reliable, and being able to more timely and accurately judge whether the water quality meets the standard.

[0063] In some embodiments of the present invention, a sewage treatment system is typically composed of multiple process sections, including pretreatment, biochemical treatment, and advanced treatment. The effluent quality of each process section may vary significantly due to different treatment processes. Therefore, step S1 first divides the discharge path of the sewage treatment system into several effluent monitoring nodes. Specifically, the discharge path of the sewage treatment system is divided into three key monitoring nodes according to the process flow:

[0064] Pretreatment node: Located at the outlet between the screen scrubber and the grit chamber, it is equipped with an online suspended solids monitor and a pH sensor to capture abnormal fluctuations during the removal of large particle pollutants.

[0065] Biochemical treatment nodes: These are located at the end of the aeration tank and the inlet weir of the secondary sedimentation tank. They are equipped with dissolved oxygen probes, ammonia nitrogen analyzers, and chemical oxygen demand rapid detection devices to monitor the core parameters of the biodegradation process.

[0066] Deep treatment node: Located at the outlet of the disinfection contact tank, it integrates an online total phosphorus analyzer, a total nitrogen detection module, and a residual chlorine sensor to ensure that the final effluent meets the standards;

[0067] A data acquisition device is set up at each outlet monitoring node to obtain the water quality characteristic parameter data of the node in real time; the setting of monitoring nodes should cover the main process sections of the sewage treatment system to ensure that the changing characteristics of water quality can be fully reflected; through multi-point monitoring, the abnormal process location can be traced more accurately, avoiding the limitation of a single monitoring point being unable to locate the problem.

[0068] Furthermore, for each selected effluent monitoring node, a weight rule library of water quality characteristic parameters needs to be preset for it. The weight rule library is a database preset for each effluent monitoring node, which is used to store the weight configuration of water quality characteristic parameters under different operating conditions. The weight reflects the importance of each water quality characteristic parameter to the comprehensive water quality assessment under specific operating conditions. By dynamically adjusting the weight, the actual water quality status can be more accurately reflected. The construction of the weight rule library is based on the operating conditions of the sewage treatment system, which mainly includes the following three dimensions:

[0069] Treatment flow range: The treatment flow of a sewage treatment plant may vary due to fluctuations in influent flow, and is divided into low-flow, medium-flow, and high-flow ranges. The importance of water quality characteristic parameters may vary in different flow ranges; for example, in the high-flow range, chemical oxygen demand and ammonia nitrogen concentration may be more important for water quality assessment;

[0070] Influent water quality category: Influent water quality may vary depending on its source, for example, the composition of industrial wastewater and domestic sewage may be different. Differences in influent water quality category will affect the weighting of certain water quality parameters. For example, when the influent water quality is mainly industrial wastewater, the weighting of total phosphorus concentration and heavy metal content may need to be increased.

[0071] Equipment load level: The operating load of sewage treatment equipment may vary depending on the equipment status or maintenance; equipment load levels are divided into low load, normal load and high load; when operating at high load, certain water quality parameters (such as dissolved oxygen concentration) may be more sensitive to water quality assessment.

[0072] The weight configuration in the weight rule base is determined through a combination of historical data analysis, expert experience and experimental verification; for example, under low flow conditions, the weights of turbidity and dissolved oxygen concentration may be higher; while under high flow conditions, the weights of chemical oxygen demand and ammonia nitrogen concentration may be higher; the construction of the weight rule base needs to fully consider the water quality change characteristics under different conditions to ensure the scientificity and rationality of the weight configuration; the weight rule base is not fixed, but can be dynamically adjusted according to the actual operation of the sewage treatment system; for example, when the effluent water quality of a certain process section is stable for a long time, the weights of certain parameters can be appropriately reduced; and when the effluent water quality of a certain process section fluctuates greatly, the weights of relevant parameters can be increased to enhance sensitivity to water quality changes.

[0073] In this embodiment, by dividing the discharge path into multiple monitoring nodes, full coverage monitoring of the sewage treatment system is achieved, avoiding the limitations of a single monitoring point; at the same time, a preset weight rule library is used to provide a basis for the subsequent calculation of the comprehensive water quality anomaly index, ensuring the comprehensiveness and accuracy of the water quality assessment; through the preset weight rule library, the weights of the water quality parameters can be dynamically adjusted according to the current operating conditions, thereby more accurately reflecting the actual water quality conditions; the construction of the weight rule library fully considers the complex working conditions of the sewage treatment system, including factors such as the amount of water treated, the quality of the influent, and the equipment load, and can adapt to the water quality change characteristics under different working conditions, thereby improving the adaptability and reliability of the water quality assessment.

[0074] In some embodiments of the present invention, in step S2, multi-source data is acquired in real time by means of a data acquisition device provided at each outlet monitoring node, including a water quality characteristic parameter set, an operating status data set of the sewage treatment system, and an environmental parameter data set. Specifically, the water quality characteristic parameter set reflects the current water quality status of each monitoring node, the operating status data set reflects the internal working conditions of the sewage treatment system, and the environmental parameter data set shows the impact of external environmental factors on the system. The above data are interrelated and together provide a basis for subsequent water quality assessment and abnormality judgment.

[0075] Among them, the water quality characteristic parameter set covers a variety of key indicators, such as pH value, turbidity, dissolved oxygen concentration, ammonia nitrogen concentration and total phosphorus concentration, which can reflect water quality characteristics from different angles; the current treated water volume and equipment operating parameters of the operating status data set are used to judge the system load and equipment status; the ambient temperature, humidity and air pressure of the environmental parameter data set will affect the physical and chemical reactions and microbial activity in the sewage treatment process to varying degrees.

[0076] For example, at the pretreatment stage, a sudden and significant increase in suspended solids concentration during a specific period may indicate malfunctioning screen scrubbers, failing to effectively intercept large particulate pollutants. Abnormal pH fluctuations may indicate a sudden change in influent quality or a deviation in the upstream treatment process. At the biochemical treatment stage, if the dissolved oxygen concentration at the end of the aeration tank remains consistently below the normal range, it can affect microbial aerobic respiration, reducing pollutant degradation efficiency and leading to elevated levels of ammonia nitrogen and chemical oxygen demand. At the advanced treatment stage, if the online total phosphorus analyzer detects total phosphorus concentrations approaching or exceeding discharge standards, it indicates ineffective phosphorus removal during the advanced treatment stage. Regarding operational data, when a sewage treatment plant is experiencing high flow rates, the equipment must process more wastewater, potentially increasing its load and reducing treatment efficiency. If, at this time, the equipment operating parameters indicate an abnormally high pump speed, this may indicate a pump failure, impacting sewage lifting and transportation. Regarding environmental parameter data, during high summer temperatures, microbial activity in the biochemical treatment tank increases, accelerating reaction rates and potentially leading to increased dissolved oxygen consumption. In high humidity environments, some electrical equipment may become damp, affecting operational stability and indirectly impacting water quality treatment.

[0077] For the collection of water quality characteristic parameters, in addition to using traditional sensors, water quality monitoring equipment based on spectral analysis can also be used; for example, an ultraviolet spectrophotometer can be used to simultaneously measure the concentrations of multiple pollutants, and by analyzing the absorbance at specific wavelengths, parameters such as chemical oxygen demand and ammonia nitrogen can be quickly obtained; for the collection of operating status data, in addition to directly collecting equipment operating parameters, its working status information can also be obtained through the equipment's intelligent control system, such as equipment fault alarm records, operating time statistics, etc.; for the collection of environmental parameters, in addition to using conventional meteorological sensors, the Internet of Things technology can also be used to obtain more accurate environmental data from surrounding meteorological monitoring stations.

[0078] In this embodiment, the multi-parameter collection of the water quality characteristic parameter set can reflect the water quality from multiple dimensions, avoid the one-sidedness of single parameter monitoring, and more accurately evaluate the water quality status; the collection of the operating status data set helps to timely discover abnormal operation and load changes of equipment inside the sewage treatment system, and prevent water quality problems caused by equipment failure or overload operation in advance; the inclusion of the environmental parameter data set fully considers the impact of the external environment on the sewage treatment process, making the water quality assessment more comprehensive; through multi-source data collection, it can provide rich and accurate data for subsequent operating condition determination, weight matching and water quality assessment, improve the reliability and accuracy of the entire sewage treatment effluent water quality real-time detection method, and help to timely discover water quality anomalies and take corresponding measures to ensure the stable operation of the sewage treatment system and the compliance of effluent water quality standards.

[0079] In some embodiments of the present invention, the operating conditions of the sewage treatment system are complex and changeable. Factors such as the amount of water treated, the type of influent water quality, and the equipment load will affect the weights of the water quality characteristic parameters. By analyzing these operating conditions in real time, the system can dynamically adjust the weight configuration to ensure the accuracy and adaptability of the water quality assessment results. Step S3 accurately identifies the current operating conditions through analysis of the operating status data and selects the most suitable weight configuration from a preset weight rule library, providing a scientific basis for the subsequent calculation of the comprehensive water quality anomaly index, as follows:

[0080] Treatment water volume range: The treatment water volume of the sewage treatment plant varies due to the fluctuation of the influent volume, and is usually divided into low flow, medium flow and high flow ranges; the low flow range (<50% of the design flow) indicates that the system load is low, the fluctuation of the water quality characteristic parameters may be small, and the weights of chemical oxygen demand and ammonia nitrogen can be appropriately reduced; for example, when the system is running at low flow at night, the chemical oxygen demand weight can be reduced (such as from 0.4 to 0.3), and the focus is on monitoring the changes in ammonia nitrogen and dissolved oxygen; the medium flow range (50%~80% of the design flow) indicates that the system is in normal operation. In the operational state, the weights of various water quality parameters can be set to default values ​​based on historical data. For example, the weight of chemical oxygen demand (COD) is 0.4, the weight of ammonia nitrogen is 0.3, and the weight of dissolved oxygen is 0.2. High flow rates (>80% of the design flow rate) indicate that the system load is high, which may lead to reduced treatment efficiency, and the weights of COD and ammonia nitrogen need to be increased. For example, if a sewage treatment plant processes 90% of the design flow rate during peak hours, the system will automatically increase the COD weight to 0.6 and the ammonia nitrogen weight to 0.4 to more sensitively capture water quality changes.

[0081] Influent water quality category: Influent water quality varies depending on its source, and the system needs to adjust weight configuration according to the water quality category. When the proportion of industrial wastewater is high, the weights of total phosphorus concentration and heavy metal content need to be increased. For example, the influent of an industrial wastewater treatment plant contains a large amount of phosphate and heavy metals. The system increases the total phosphorus weight from 0.1 to 0.3 and the heavy metal weight from 0.2 to 0.4. When the proportion of domestic sewage is high, the weights of nitrogen and phosphorus parameters are higher. For example, the influent of a domestic sewage treatment plant is mainly domestic sewage. The system increases the ammonia nitrogen weight from 0.3 to 0.5 and the total phosphorus weight from 0.1 to 0.2.

[0082] Equipment load level: The equipment load level reflects the operating status of the sewage treatment equipment. When operating at high load, the weight of dissolved oxygen concentration needs to be increased because aeration efficiency may decrease, affecting the aerobic respiration of microorganisms. For example, when a sewage treatment plant is operating at high load, the system increases the dissolved oxygen weight from 0.2 to 0.4 to ensure that the degradation efficiency of microorganisms is not affected.

[0083] For example, in the high flow range, the system recognizes the increase in treated water volume and automatically increases the weights of chemical oxygen demand and ammonia nitrogen; for example, a sewage treatment plant treats 90% of the design flow during peak hours, and the system matches the weight configuration of high flow conditions, increasing the chemical oxygen demand weight from 0.3 to 0.5 and the ammonia nitrogen weight from 0.2 to 0.4 to more accurately reflect water quality changes; when the influent water quality category is industrial wastewater, the system recognizes an abnormal increase in total phosphorus concentration and automatically increases the total phosphorus weight; for example, the total phosphorus concentration in the wastewater discharged by a factory exceeds the standard, and the system increases the total phosphorus weight from 0.1 to 0.3 to ensure that the impact of total phosphorus on the comprehensive water quality assessment is more significant.

[0084] At the same time, machine learning algorithms can be used to classify operating conditions; for example, historical data can be used to train a classification model to classify operating conditions into categories such as "normal conditions", "high load conditions", and "low load conditions" to automatically identify the current conditions; fuzzy logic models can also be used to fuzzy classify operating conditions; for example, the treated water volume, influent water quality, and equipment load are used as input variables, and the fuzzy membership of the current conditions is determined through fuzzy logic reasoning, thereby selecting the weight configuration.

[0085] In this embodiment, the system can dynamically adjust the weight configuration according to the real-time operating status of the sewage treatment system to ensure that the water quality assessment results can adapt to changes in different working conditions; for example, under high flow conditions, the system automatically increases the weights of chemical oxygen demand and ammonia nitrogen, which can more sensitively capture water quality changes and avoid assessment errors caused by fixed weights; through operating condition analysis, the system can accurately match the weight configuration suitable for the current working conditions to ensure that the weights of water quality characteristic parameters are consistent with their actual impact; for example, under conditions where the proportion of industrial wastewater is high, the system increases the total phosphorus and heavy metal Weights can more accurately reflect water quality conditions; dynamic weight adjustment can reduce misjudgments or missed judgments caused by fixed weights, and improve the reliability of water quality assessment; for example, under low flow conditions, the system reduces the weights of turbidity and dissolved oxygen to avoid abnormal alarms caused by small fluctuations; the system can comprehensively consider multi-dimensional factors such as treated water volume, influent water quality and equipment load, and adapt to water quality assessment needs under complex working conditions; for example, under high flow and mixed industrial wastewater conditions, the system can simultaneously increase the weights of chemical oxygen demand, ammonia nitrogen and total phosphorus to ensure the comprehensiveness of water quality assessment.

[0086] In some embodiments of the present invention, water quality characteristic parameter data is deeply integrated and analyzed with parameter weight configurations matched according to operating conditions to generate a comprehensive water quality anomaly index corresponding to each effluent monitoring node; in the sewage treatment process, the degree of influence of the water quality characteristic parameters of each monitoring node on the overall water quality changes dynamically with the operating conditions; therefore, it is necessary to associate the pH value, turbidity, dissolved oxygen concentration, ammonia nitrogen concentration, total phosphorus concentration and other water quality characteristic parameters collected in real time with the specific weight configuration determined in step S3 for different operating conditions; by constructing a scientific mathematical model, the importance of each parameter under the current operating conditions is comprehensively weighed, and then a quantitative index that can accurately reflect the degree to which the water quality of the monitoring node deviates from the normal state is obtained; this index is not a simple stacking of parameters, but a scientific calculation result based on the weight differences of each parameter, which can significantly improve the accuracy of judging abnormal water quality conditions.

[0087] Specifically, the calculation formula of the water quality comprehensive abnormality index is designed as follows: in, represents the comprehensive abnormal water quality index corresponding to the j-th outlet monitoring node, represents the real-time collected value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node; represents the standard limit of the i-th water quality characteristic parameter corresponding to the j-th outlet monitoring node; It represents the weight value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node. The weight value is obtained from the weight rule library according to the current operating conditions. n represents the total number of characteristic parameters in the water quality characteristic parameter set corresponding to the j-th outlet water monitoring node. k represents the nonlinear dynamic index factor, which is used to enhance the sensitivity of the exceeding parameters.

[0088] In this embodiment, by considering the real-time collection values, standard limits, weight values ​​and nonlinear dynamic index factors of water quality characteristic parameters, the actual water quality situation, water quality standard requirements, differences in parameter importance under different working conditions and special treatment of exceeding standard conditions are comprehensively covered, and water quality abnormal conditions can be comprehensively and systematically reflected; the weight values ​​are obtained from the weight rule library according to the current operating conditions; this makes the contribution of each water quality characteristic parameter to the comprehensive water quality abnormality index different under different operating conditions, and can more accurately reflect the actual situation of water quality under different working conditions; for example, under the working condition with a high proportion of industrial wastewater, the weight of the parameter related to the industrial wastewater pollution factor will increase, and the corresponding impact on the comprehensive water quality abnormality index will be greater; by introducing the nonlinear dynamic index factor, the calculation results can be affected to varying degrees according to the degree of exceeding the standard of the water quality characteristic parameter; for parameters that significantly exceed the standard, a higher amplification factor is given to highlight their impact on water quality abnormalities and enhance the ability to capture water quality abnormalities.

[0089] More specifically, the calculation formula of the nonlinear dynamic index factor k is:

[0090] ;

[0091] By setting a nonlinear dynamic index factor, when the ratio of the real-time collected value of the water quality characteristic parameter to the standard limit is ≥1.2 (i.e., significantly exceeded by ≥20%), k=1.5 is used, otherwise k=1.2 is used. This can increase its influence in the calculation of the comprehensive water quality anomaly index for exceeding the standard, especially for serious exceeding of the standard, making anomaly detection more sensitive and helping to promptly discover and pay attention to serious water quality anomalies.

[0092] In some embodiments of the present invention, an environmental compensation coefficient is calculated based on environmental parameter data and operating status data, and the coefficient is used to correct the comprehensive water quality anomaly index to obtain a corrected anomaly index; the introduction of the environmental compensation coefficient is to eliminate the interference of external environmental factors on water quality assessment and ensure the reliability of water quality assessment results; environmental parameter data include ambient temperature, humidity, and air pressure, etc. These factors will affect the physical and chemical reactions and microbial activity in the sewage treatment process; operating status data reflects the actual operation of the sewage treatment system, such as the amount of water treated and equipment operating parameters; the calculation of the environmental compensation coefficient is based on a preset environmental compensation model, which is trained by a deep learning algorithm and can output a compensation coefficient based on environmental parameters and operating status data; by multiplying the comprehensive water quality anomaly index by the compensation coefficient, the corrected anomaly index can be obtained, thereby more accurately reflecting the actual condition of the water quality; specifically, the calculation formula of the environmental compensation model is as follows:

[0093] ;

[0094] in, Represents the energy change caused by temperature change; Indicates real-time temperature; Indicates the reference temperature; represents the temperature sensitivity coefficient;

[0095] Represents the energy change caused by humidity change; Indicates real-time humidity; Represents the humidity sensitivity coefficient;

[0096] It represents the energy change caused by pressure change; Indicates real-time pressure; Indicates standard pressure; Indicates the pressure sensitivity coefficient; Indicates the dissolved oxygen activation flag, with a value of 0 or 1, indicating whether compensation is enabled;

[0097] Indicates the energy change caused by the change of sewage treatment flow; Indicates real-time sewage treatment flow; Indicates the maximum flow rate; Indicates rated flow; It represents the flow sensitivity coefficient;

[0098] Indicates the energy change caused by the equipment load level; Indicates the real-time equipment load level, such as the aerator power percentage; Indicates the equipment load level sensitivity coefficient;

[0099] represents the environmental compensation coefficient; 、 、 、 and represent the normalized functions of temperature, humidity, pressure, sewage treatment flow rate, and equipment load level respectively;

[0100] Afterwards, the comprehensive water quality anomaly index calculated in step S4 is multiplied by the environmental compensation coefficient to obtain a corrected anomaly index, thereby more accurately reflecting the actual status of the water quality at the outlet monitoring node.

[0101] In this embodiment, multiple environmental parameter data such as ambient temperature, humidity, and air pressure are included in the calculation; temperature changes will affect microbial activity and chemical reaction rate, such as microbial activity decreases at low temperatures and sewage treatment efficiency decreases; humidity changes may affect the equipment operating environment and biochemical reaction conditions at high humidity; air pressure changes will affect reactions involving gas exchange, such as the acquisition of dissolved oxygen; comprehensive consideration of the above environmental factors can more accurately reflect the comprehensive impact of the external environment on sewage treatment; operating status factors include operating status data such as treated water volume and equipment operating parameters; changes in treated water volume will affect water flow rate, residence time, etc., thereby changing the treatment effect; different equipment load levels, such as changes in aerator power percentage, will directly affect the oxygen supply conditions and biochemical reaction processes of microorganisms; by combining these operating status factors, the impact of the actual operating conditions within the sewage treatment system on water quality can be accurately grasped; different sensitivity coefficients are set for different influencing factors, such as temperature, The temperature sensitivity coefficient, humidity sensitivity coefficient, etc. can be adjusted and optimized according to the actual situation, regional characteristics, equipment characteristics, etc. of the sewage treatment plant, so that the model can better adapt to different scenarios and improve the accuracy of the calculation; for example, in cold areas, the temperature sensitivity coefficient can be appropriately increased to highlight the impact of temperature on water quality; for the calculation of energy changes caused by humidity changes, set humidity condition judgment (H≥80%); when the humidity reaches a certain level, the corresponding calculation is performed, otherwise it is 0, which can avoid unnecessary calculations when the humidity impact is small, and accurately capture the significant impact that high humidity may have on water quality; by setting a normalization function, the energy changes caused by different influencing factors are standardized; due to the different dimensions and numerical ranges of different factors, such as temperature, flow, equipment load level, etc., standardization can unify these factors to the same calculation scale, avoid calculation deviations due to dimensional differences, and ensure the scientificity and accuracy of the environmental compensation coefficient calculation.

[0102] In some embodiments of the present invention, the corrected anomaly index after environmental compensation is compared with a preset water quality compliance threshold; if the corrected anomaly index exceeds the set threshold, it indicates that the current water quality condition does not meet the expected standard, and it is necessary to trigger an over-standard warning and locate the specific abnormal water outlet monitoring node; on the contrary, if the corrected anomaly index is within the threshold range, it means that the water quality meets the requirements, and the system will continue to perform steps such as data collection and anomaly index calculation; the water quality compliance threshold is set based on national or local environmental protection laws and regulations, industry standards or specific process requirements of sewage treatment plants; the water quality compliance threshold not only takes into account the safety limits of water quality characteristic parameters, but also combines the dynamic adjustment needs under actual operating conditions to ensure that the evaluation results are both strict and reasonable.

[0103] For example, suppose a sewage treatment plant is at its peak in summer. After calculation in steps S4 and S5, the corrected anomaly index is 11.0. Assuming that the plant's water quality threshold is set at 10.0 (hypothetically), the corrected anomaly index exceeds the threshold. The system triggers an over-standard alert and locates the specific anomaly point by analyzing the data from each effluent monitoring node. For example, it is found that the dissolved oxygen concentration at the end of the aeration tank is continuously below the normal range, resulting in increased ammonia nitrogen and chemical oxygen demand indicators, affecting the overall water quality.

[0104] In this embodiment, the corrected abnormality index is combined with the influence of the environmental compensation coefficient to more accurately reflect the actual water quality conditions; by comparing with the preset water quality threshold, it can effectively avoid misjudgment or omission caused by relying solely on the original water quality data, and improve the reliability of the early warning system; an accurate over-standard early warning mechanism helps to discover and solve problems in a timely manner, reducing fines and other economic losses caused by substandard water quality; at the same time, by accurately locating the abnormal water outlet monitoring node, targeted measures can be taken to avoid the waste of resources caused by blind inspections; according to the changing trend of the corrected abnormality index, management personnel can more specifically adjust resource allocation and operation strategies; for example, increase the aeration volume during high temperatures to maintain good water quality treatment effects, or take insulation measures under low temperature conditions to ensure microbial activity, thereby achieving optimal resource allocation.

[0105] In some schemes, multiple embodiments of the present application can be combined and the combined scheme can be implemented. Optionally, some operations in the process of each method embodiment are optionally combined, and / or the order of some operations is optionally changed. In addition, the execution order between the steps of each process is only exemplary and does not constitute a limitation on the execution order between the steps. There can also be other execution orders between the steps. It is not intended to indicate that the execution order is the only order in which these operations can be performed. Ordinary technicians in this field will think of many ways to reorder the operations described herein. In addition, it should be noted that the process details involved in a certain embodiment of this article are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.

[0106] Furthermore, some steps in the method embodiments may be equivalently replaced with other possible steps. Alternatively, some steps in the method embodiments may be optional and may be deleted in certain usage scenarios. Alternatively, other possible steps may be added to the method embodiments. Furthermore, the various method embodiments may be implemented separately or in combination.

[0107] like Figure 2 As shown, the present invention also provides a real-time detection system for sewage treatment effluent quality, which specifically includes the following modules:

[0108] A monitoring node module is used to divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes and preset a weight rule library of water quality characteristic parameters for each effluent monitoring node; the weight rule library is used to store the weight configuration of each water quality characteristic parameter under different operating conditions;

[0109] The data acquisition module is used to collect the water quality characteristic parameter set of each effluent monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set in real time;

[0110] An operating condition analysis module, configured to determine a current operating condition based on the operating status data of the sewage treatment system, and to match corresponding parameter weight configurations in the weight rule library based on the current operating condition;

[0111] The anomaly index calculation module is used to perform weighted calculation on the water quality characteristic parameter data and the matching parameter weight configuration to generate a comprehensive water quality anomaly index corresponding to each water outlet monitoring node; the comprehensive water quality anomaly index is used to characterize the water quality anomaly level of the current monitoring node;

[0112] A compensation module is used to input environmental parameter data and operating status data into a preset environmental compensation model, output an environmental compensation coefficient, and compensate and correct the comprehensive water quality abnormality index according to the environmental compensation coefficient to obtain a corrected abnormality index, wherein the corrected abnormality index is used to reflect the abnormal level of water quality after considering environmental factors;

[0113] The alarm module is used to compare the corrected abnormal index with the preset water quality threshold; if the corrected abnormal index exceeds the water quality threshold, an over-standard warning is triggered and the abnormal water outlet monitoring node is located; otherwise, the data collection and abnormal index calculation steps are continuously executed.

[0114] In this embodiment, multi-node monitoring covers the entire discharge path of the sewage treatment system, which can accurately locate the abnormal process location and improve the efficiency of abnormal investigation; the weights of water quality characteristic parameters are dynamically adjusted according to the operating conditions of the sewage treatment system, which can adapt to the water quality change characteristics under different working conditions and improve the accuracy of water quality assessment; the impact of environmental factors on water quality is corrected through the environmental compensation model, external interference is eliminated, and the reliability of detection results is improved; the water quality status can be judged in real time, and an early warning can be quickly triggered when it exceeds the standard, and abnormal nodes can be located at the same time to provide support for timely treatment measures; through dynamic weight adjustment and continuous optimization of the environmental compensation model, it has strong adaptive capabilities; at the same time, the system supports the expansion of monitoring nodes and is suitable for sewage treatment systems of different sizes.

[0115] This embodiment divides the functional modules according to the above-described method example. For example, each functional module can be divided according to its function, or two or more functions can be integrated into a single processing module. The integrated modules can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used.

[0116] The various variations and specific embodiments of the real-time detection method for sewage treatment effluent quality in the aforementioned embodiments are also applicable to the real-time detection system for sewage treatment effluent quality in this embodiment. Through the aforementioned detailed description of the real-time detection method for sewage treatment effluent quality, those skilled in the art can clearly understand the implementation method of the real-time detection system for sewage treatment effluent quality in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0117] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time detection method for sewage treatment effluent quality, characterized in that: The method is applied to a sewage treatment system, and comprises: Divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes, and preset a weight rule library of water quality characteristic parameters for each of the effluent monitoring nodes; Real-time collection of the water quality characteristic parameter set of each outlet monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set; Determine the current operating condition of the sewage treatment system based on the operating status data, and match the corresponding parameter weight configuration in the weight rule library based on the current operating condition of the sewage treatment system; Performing weight analysis on the water quality characteristic parameter data and the parameter weight configuration to generate a comprehensive water quality anomaly index corresponding to the outlet water monitoring node; Inputting the environmental parameter data and the operating status data into a preset environmental compensation model, outputting an environmental compensation coefficient, and compensating and correcting the comprehensive water quality abnormality index based on the coefficient to obtain a corrected abnormality index; Compare the corrected abnormal index with the preset water quality threshold: If the corrected abnormality index exceeds the threshold, an over-standard warning is triggered and the abnormal water discharge monitoring node is located; otherwise, the data collection and abnormality index calculation steps are continuously executed; The weight rule library contains parameter weight configurations corresponding to different operating conditions, including the treated water volume range, influent water quality category, and equipment load level; The calculation formula of the environmental compensation model is: ； in, Represents the energy change caused by temperature change; Indicates real-time temperature; Indicates the reference temperature; represents the temperature sensitivity coefficient; Represents the energy change caused by humidity change; Indicates real-time humidity; Indicates the humidity sensitivity coefficient; It represents the energy change caused by pressure change; Indicates real-time pressure; Indicates standard pressure; Indicates the pressure sensitivity coefficient; Indicates the dissolved oxygen activation flag, with a value of 0 or 1, indicating whether compensation is enabled; Indicates the energy change caused by the change of sewage treatment flow; Indicates real-time sewage treatment flow; Indicates the maximum flow rate; Indicates rated flow; It represents the flow sensitivity coefficient; Indicates the energy change caused by the equipment load level; Indicates the real-time equipment load level; Indicates the equipment load level sensitivity coefficient; represents the environmental compensation coefficient; 、 、 、 and represent the normalized functions of temperature, humidity, pressure, sewage treatment flow rate, and equipment load level respectively; Multiply the comprehensive water quality anomaly index by the environmental compensation coefficient to obtain the corrected anomaly index.

2. The method for real-time detection of sewage treatment effluent quality according to claim 1, characterized in that: The water quality characteristic parameter set includes at least any two of pH value, turbidity, dissolved oxygen concentration, ammonia nitrogen concentration and total phosphorus concentration; The operating status data set includes at least the current treated water volume and equipment operating parameters; The environmental parameter data set includes at least environmental temperature, environmental humidity and environmental pressure.

3. The method for real-time detection of sewage treatment effluent quality according to claim 2, characterized in that: The calculation formula of the comprehensive water quality abnormality index is: ； in, represents the comprehensive abnormal water quality index corresponding to the j-th outlet monitoring node, represents the real-time collected value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node; represents the standard limit of the i-th water quality characteristic parameter corresponding to the j-th outlet monitoring node; It represents the weight value of the i-th water quality characteristic parameter corresponding to the j-th outlet water monitoring node. The weight value is obtained from the weight rule library according to the current operating conditions. n represents the total number of characteristic parameters in the water quality characteristic parameter set corresponding to the j-th outlet water monitoring node. k represents the nonlinear dynamic index factor, which is used to enhance the sensitivity of the exceeding parameters.

4. The method for real-time detection of sewage treatment effluent quality according to claim 3, characterized in that: The calculation formula of the nonlinear dynamic index factor k is: ； By setting the nonlinear dynamic index factor, when the ratio of the real-time collected value of the water quality characteristic parameter to the standard limit is ≥1.2, k=1.5 is used, otherwise k=1.2 is used.

5. The method for real-time detection of sewage treatment effluent quality according to claim 1, characterized in that: The weight rule library for presetting the water quality characteristic parameters for each outlet water monitoring node includes: Based on the historical operation data of the sewage treatment system, analyze the water quality change characteristics of different treatment process sections and determine the influence weight of each water quality characteristic parameter on water quality under different working conditions; According to the influence weight, a weight rule library is constructed using a machine learning algorithm, and the machine learning algorithm includes at least one of a support vector machine, a random forest, or a gradient boosting tree.

6. The method for real-time detection of sewage treatment effluent quality according to claim 5, characterized in that: The real-time collection of the water quality characteristic parameter set of each effluent monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set includes: A distributed sensor network is used to deploy multiple types of sensors at each of the outlet water monitoring nodes, wherein the sensors include at least two of optical sensors, electrochemical sensors, and microbial sensors; By interacting with the sewage treatment system's automatic control system and environmental monitoring system, the system can obtain real-time operating status data and environmental parameter data, and perform real-time verification and cleaning on the collected data to remove outliers and noise data.

7. The method for real-time detection of sewage treatment effluent quality according to claim 5, characterized in that: Determining the current operating condition of the sewage treatment system according to the operating status data, and matching the corresponding parameter weight configuration in the weight rule library based on the current operating condition of the sewage treatment system, includes: Perform feature extraction and feature engineering on the operating status data to construct a feature vector reflecting the operating status of the sewage treatment system; Using a clustering algorithm to divide the feature vectors into different operating condition categories, the clustering algorithm includes at least one of K-Means clustering, DBSCAN clustering, and Gaussian mixture model clustering; According to the current operating condition category, the corresponding parameter weight configuration is matched in the weight rule library.

8. A real-time detection system for sewage treatment effluent quality, characterized in that: The system is applied to the real-time detection method for sewage treatment effluent quality according to claim 1, comprising: A monitoring node module is used to divide the discharge path of the sewage treatment system into at least two effluent monitoring nodes and preset a weight rule library of water quality characteristic parameters for each effluent monitoring node; The data acquisition module is used to collect the water quality characteristic parameter set of each effluent monitoring node, the operating status data set of the sewage treatment system, and the environmental parameter data set in real time; An operating condition analysis module, configured to determine a current operating condition based on the operating status data of the sewage treatment system, and to match corresponding parameter weight configurations in the weight rule library based on the current operating condition; The abnormal index calculation module is used to perform weighted calculation on the water quality characteristic parameter data and the matching parameter weight configuration to generate the comprehensive water quality abnormal index corresponding to each outlet monitoring node; The compensation module is used to input the environmental parameter data and the operating status data into a preset environmental compensation model, output the environmental compensation coefficient, and compensate and correct the comprehensive water quality abnormality index according to the environmental compensation coefficient to obtain the corrected abnormality index; The alarm module is used to compare the corrected abnormal index with the preset water quality threshold; if the corrected abnormal index exceeds the water quality threshold, an over-standard warning is triggered and the abnormal water outlet monitoring node is located; otherwise, the data collection and abnormal index calculation steps are continuously executed.

Images