A method and system for monitoring the progress of sewage treatment

Abstract

The present invention provides a method and system for monitoring the sewage treatment progress. By collecting and processing the first water quality parameter values of key nodes of sewage treatment facilities in a historical time period, a dynamic model of the sewage treatment process is constructed using a deep neural network, and a genetic algorithm is introduced to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model. The optimized dynamic model is used to predict the sewage treatment effect, and prediction results and operation data of the sewage treatment facilities are obtained. The fuzzy logic control algorithm is used to adjust the setting values of the operation parameters of the sewage treatment system, and the support vector machine algorithm is used to classify and identify the fault modes of the sewage treatment system to obtain fault classification results. Based on the prediction results, operation data, optimized operation parameter setting values, and fault classification results, a comprehensive monitoring and management system based on a cloud platform is constructed. The present invention realizes the comprehensive monitoring and fault identification of the sewage treatment process, ensuring the efficient, stable, and reliable operation of sewage treatment.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of water treatment, and in particular, to a method and system for monitoring the progress of sewage treatment. Background Art

[0002] With the acceleration of the industrialization process and the advancement of urbanization, the problem of water pollution has become increasingly serious. As an important link in environmental protection, the efficiency and quality of sewage treatment directly affect the sustainable utilization of water resources and the maintenance of ecological balance. Sewage treatment is widely used in urban sewage treatment plants, industrial wastewater treatment stations and other places. In these application scenarios, real-time monitoring and optimization of the sewage treatment process are crucial.

[0003] Currently, the monitoring of the progress of sewage treatment mainly relies on manual sampling analysis and on-line monitoring instruments. Manual sampling analysis is time-consuming and costly, and cannot provide continuous data streams, making it difficult to detect instantaneous changes or abnormalities in the sewage treatment process in a timely manner; on-line monitoring instruments such as on-line chemical oxygen demand detectors and on-line ammonia nitrogen detectors are easily affected by non-target substances when facing complex sewage components, resulting in measurement result deviations. High-end on-line monitoring equipment not only has a high purchase cost, but also has high later operation and maintenance costs, which limits its application in small and medium-sized sewage treatment stations. Summary of the Invention

[0004] The embodiments of the present invention provide a method and system for monitoring the progress of sewage treatment, which are used to solve the problems of discontinuous data collection, weak anti-interference ability, inaccurate measurement results and high input costs in the prior art.

[0005] In a first aspect, the embodiments of the present invention provide a method for monitoring the progress of sewage treatment, including:

[0006] Receiving real-time data streams from different sources, the real-time data streams including structured data and unstructured data;

[0007] Collecting the first water quality parameter values of key nodes of sewage treatment facilities within a historical time period;

[0008] Performing data processing on the first water quality parameter values, and based on the processed first water quality parameter values, constructing a dynamic model of the sewage treatment process by using a deep neural network, and introducing a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and using the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facilities;

[0009] Dynamically adjust the set values of the operating parameters of the sewage treatment system to which the sewage treatment facility belongs by using a fuzzy logic control algorithm to obtain optimized set values of the operating parameters. Based on the optimized set values of the operating parameters, classify and identify the fault modes of the sewage treatment system during the sewage treatment process through a support vector machine algorithm to obtain a fault classification result;

[0010] Based on the prediction result, the operation data, the optimized set values of the operating parameters, and the fault classification result, construct a comprehensive monitoring and management system based on a cloud platform. The comprehensive monitoring and management system integrates an expert system and a user-defined alarm rule function to achieve automatic monitoring of the sewage treatment process.

[0011] Optionally, the dynamically adjusting the set values of the operating parameters of the sewage treatment system to which the sewage treatment facility belongs by using a fuzzy logic control algorithm to obtain optimized set values of the operating parameters, and based on the optimized set values of the operating parameters, classifying and identifying the fault modes of the sewage treatment system during the sewage treatment process through a support vector machine algorithm to obtain a fault classification result includes:

[0012] Based on the prediction result and the operation data, collect real-time second water quality parameter values and set values of the operating parameters of the sewage treatment system to which the sewage treatment facility belongs to obtain real-time data;

[0013] Based on the real-time data, set the input variables of the fuzzy logic control algorithm. The input variables include water quality parameters and operating parameters. The water quality parameters include pH value, dissolved oxygen, and chemical oxygen demand. The operating parameters include aeration volume and chemical agent dosing ratio;

[0014] Define fuzzy rules, apply the fuzzy logic control algorithm, and perform fuzzy reasoning according to the input variables and the fuzzy rules to obtain optimized set values of the operating parameters to optimize the sewage treatment effect;

[0015] Based on the optimized set values of the operating parameters and the second water quality parameter values, train a support vector machine model to identify and classify fault modes to obtain a fault classification result.

[0016] Optionally, the defining fuzzy rules, applying the fuzzy logic control algorithm, and performing fuzzy reasoning according to the input variables and the fuzzy rules to obtain optimized set values of the operating parameters to optimize the sewage treatment effect includes:

[0017] Define fuzzy sets, use membership functions to convert the second water quality parameter values and set values of the operating parameters in the input variables into membership degrees of the fuzzy sets;

[0018] Define fuzzy rules based on the fuzzy sets and membership degrees;

[0019] Apply the fuzzy logic control algorithm, perform fuzzy inference according to the fuzzy rules and the fuzzy sets, calculate the optimal operating parameter setting values, and use the defuzzification method to process the optimal operating parameter setting values to obtain the optimized operating parameter setting values.

[0020] Optionally, based on the prediction result, the operation data, the optimized operating parameter setting values, and the fault classification result, construct an integrated monitoring and management system based on the cloud platform. The integrated monitoring and management system integrates an expert system and a user-defined alarm rule function to realize the automatic monitoring of the sewage treatment process, including:

[0021] Integrate and clean the data of the prediction result, the operation data, the optimized operating parameter setting values, and the fault classification result to obtain sewage treatment data;

[0022] Based on the sewage treatment data, use the front-end display technology of the cloud platform to display the status and prediction trend of sewage treatment in real time to provide a monitoring interface;

[0023] Integrate an expert system. The expert system combines the target expert knowledge base to provide the optimal operation strategy corresponding to the status of sewage treatment;

[0024] Generate a user interface to enable users to set custom alarm rules according to actual needs and the user-defined alarm rule function. The custom alarm rules include different thresholds and alarm conditions. When the second water quality parameter value or the optimized operating parameter setting value in the real-time data exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and processing;

[0025] Based on the sewage treatment data, the monitoring interface, the expert system, and the user interface, construct an integrated monitoring and management system based on the cloud platform to realize the automatic monitoring of sewage treatment.

[0026] Optionally, the integrated expert system combines the target expert knowledge base to provide the optimal operation strategy corresponding to the status of sewage treatment, including:

[0027] Formulate fault diagnosis rules according to historical data, where the historical data includes the first water quality parameter value;

[0028] Based on the fault classification result and the fault diagnosis rules, formulate known optimal operation strategies for different fault types;

[0029] Based on the fault diagnosis rules and the known optimal operation strategies, construct an initial expert knowledge base, introduce an adaptive learning mechanism, and optimize the expert knowledge base to obtain the target expert knowledge base;

[0030] Determine an optimal operation strategy corresponding to the state of sewage treatment based on the target expert knowledge base.

[0031] Optionally, generate a user interface to enable the user to set a custom alarm rule according to actual needs and the user-defined alarm rule function. The custom alarm rule includes different thresholds and alarm conditions. When the value of the second water quality parameter or the optimized operating parameter setting value in the real-time data exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and processing, including:

[0032] Generate a user interface to enable the user to set a custom alarm rule according to actual needs and the user-defined alarm rule function. The custom alarm rule includes different thresholds and alarm conditions;

[0033] Based on the custom alarm rule, when the value of the second water quality parameter or the optimized operating parameter setting value in the real-time data exceeds the corresponding preset range, an alarm is triggered, and the user is notified in real time through multiple notification channels, and real-time alarm information is generated;

[0034] Based on the real-time alarm information, select the corresponding quick response mechanism and the optimal operation strategy to achieve real-time response and processing.

[0035] Optionally, perform data processing on the value of the first water quality parameter, and based on the processed value of the first water quality parameter, construct a dynamic model of the sewage treatment process using a deep neural network, and introduce a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model. Use the optimized dynamic model to predict the sewage treatment effect, and obtain a prediction result and the operating data of the sewage treatment facility, including:

[0036] Perform data normalization processing on the value of the first water quality parameter, extract key information from the normalized data to obtain the processed value of the first water quality parameter, and based on the processed value of the first water quality parameter, construct a dynamic model of the sewage treatment process using a deep neural network. Use a genetic algorithm to adjust the weights, biases, the number of layers of the neural network, and the number of neurons in each layer to optimize the structure and parameters of the dynamic model to obtain a preliminarily optimized dynamic model;

[0037] Use the processed value of the first water quality parameter to train the preliminarily optimized dynamic model to obtain an optimized dynamic model. Use the optimized dynamic model to predict the sewage treatment effect, and obtain a prediction result and the operating data of the sewage treatment facility.

[0038] In a second aspect, an embodiment of the present invention provides a monitoring system for the progress of sewage treatment, including:

[0039] A collection module for collecting the first water quality parameter values of key nodes of a sewage treatment facility within a historical time period;

[0040] An optimization module for processing the first water quality parameter values, constructing a dynamic model of the sewage treatment process using a deep neural network based on the processed first water quality parameter values, introducing a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and using the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility;

[0041] An identification module for dynamically adjusting the set value of the operation parameters of the sewage treatment system to which the sewage treatment facility belongs using a fuzzy logic control algorithm to obtain an optimized set value of the operation parameters, and classifying and identifying the fault modes of the sewage treatment system during the sewage treatment process through a support vector machine algorithm based on the optimized set value of the operation parameters to obtain a fault classification result;

[0042] A construction module for constructing a cloud platform-based integrated monitoring and management system based on the prediction result, the operation data, the optimized set value of the operation parameters, and the fault classification result, where the integrated monitoring and management system integrates an expert system and a user-defined alarm rule function to achieve automatic monitoring of the sewage treatment process.

[0043] In a third aspect, an embodiment of the present invention provides a computing device including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the monitoring method for the progress of sewage treatment according to any one of the first aspect.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the monitoring method for the progress of sewage treatment according to any one of the first aspect is implemented.

[0045] In an embodiment of the present invention, the first water quality parameter values at key nodes of a sewage treatment facility are collected within a historical time period; the first water quality parameter values are processed, and based on the processed first water quality parameter values, a dynamic model of the sewage treatment process is constructed using a deep neural network, and a genetic algorithm is introduced to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model. The optimized dynamic model is used to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility; a fuzzy logic control algorithm is used to dynamically adjust the set values of the operation parameters of the sewage treatment system to which the sewage treatment facility belongs to obtain optimized set values of the operation parameters. Based on the optimized set values of the operation parameters, a support vector machine algorithm is used to classify and identify the fault modes of the sewage treatment system during the sewage treatment process to obtain a fault classification result; based on the prediction result, the operation data, the optimized set values of the operation parameters, and the fault classification result, a comprehensive monitoring and management system based on a cloud platform is constructed. The comprehensive monitoring and management system integrates an expert system and a user-defined alarm rule function to realize the automatic monitoring of the sewage treatment process. The technical solution provided by the present invention realizes the comprehensive monitoring, optimization, and fault identification of the sewage treatment process, improves the intelligent level and management level of the system, and ensures the efficient, stable, and reliable operation of sewage treatment. Among them, through the fuzzy logic control algorithm, the set values of the operation parameters of the sewage treatment system are adjusted and optimized in real time to improve the treatment effect and system stability; the fuzzy logic control algorithm can process uncertain and inaccurate information, making the control more flexible and accurate; by optimizing the operation parameters, the occurrence of system faults is reduced, and the reliability and safety of the system are improved; the optimized set values of the operation parameters can reduce unnecessary aeration volume and chemical agent dosage, reduce energy consumption and chemical agent costs, and achieve energy conservation and emission reduction; combining the fuzzy logic control and defuzzification methods, the intelligent management of the sewage treatment process is realized, and the automation level and management level are improved.

[0046] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a flowchart of a method for monitoring the sewage treatment progress provided by an embodiment of the present invention;

[0049] Figure 2Schematic structural diagram of a sewage treatment progress monitoring system provided by an embodiment of the present invention;

[0050] Figure 3 Schematic structural diagram of a computing device provided by an embodiment of the present invention. Detailed implementation manners

[0051] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0052] In some processes described in the specification, claims and above-mentioned drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] Figure 1 Flowchart of a sewage treatment progress monitoring method provided by an embodiment of the present invention, as Figure 1 shown, the method includes:

[0055] In order to solve the problems of discontinuous data collection, weak anti-interference ability and high cost in the existing sewage treatment progress monitoring, and improve the technical level and environmental governance efficiency of the sewage treatment industry. Based on this, the present invention provides a sewage treatment progress monitoring method, as Figure 1 , including:

[0056] Step 101: Collect the first water quality parameter values of the key nodes of the sewage treatment facilities within a historical time period;

[0057] In this step, key nodes refer to important monitoring locations in the sewage treatment process, such as the inlet, aeration tank, sedimentation tank, outlet, etc. The water quality parameters at these locations can reflect the state of the entire treatment process; the first water quality parameter value refers to the water quality data collected from key nodes within a specific time period, such as biochemical oxygen demand (BOD), suspended solids (SS), pH value, ammonia nitrogen, etc.

[0058] This step determines the key nodes in the sewage treatment facility, such as the inlet, aeration tank, sedimentation tank, outlet, etc.; then, within the historical time period, water quality parameter values, such as COD, BOD, SS, pH value, ammonia nitrogen, etc., are regularly collected from these key nodes, and these data will be used as the basis for subsequent modeling.

[0059] Suppose the data of the past year is selected, then the water quality parameter values are collected once a day from each key node, and these data are stored in a database for subsequent processing.

[0060] Step 102: Process the first water quality parameter values, and based on the processed first water quality parameter values, construct a dynamic model of the sewage treatment process using a deep neural network, and introduce a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model. Use the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility;

[0061] In this step, a deep neural network refers to a multi-layer artificial neural network used to learn and model complex non-linear relationships and is suitable for processing a large amount of high-dimensional data. A genetic algorithm refers to an optimization algorithm that simulates natural selection and genetic mechanisms and is used to search for the optimal solution and is often used to optimize the structure and parameters of a model. A dynamic model refers to a mathematical model that describes the change of a system over time and is used to predict the future state of the system.

[0062] This step processes the first water quality parameter values collected, including data cleaning, normalization, and missing value filling. Data cleaning, such as removing outliers and noise, normalization, such as converting data with different dimensions to the same dimension, and missing value filling, such as using interpolation or other methods to fill in missing data, etc.; use the processed first water quality parameter values to construct a deep neural network model to describe the dynamic changes of the sewage treatment process. For example, the deep neural network model can use a multi-layer perceptron (MLP) or a convolutional neural network (CNN); introduce a genetic algorithm to optimize the structure and parameters of the model to obtain an optimized dynamic model; use the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility.

[0063] Step 103: Dynamically adjust the set values of the operating parameters of the sewage treatment system to which the sewage treatment facilities belong by using the fuzzy logic control algorithm to obtain the optimized set values of the operating parameters. Based on the optimized set values of the operating parameters, classify and identify the fault modes of the sewage treatment system during the sewage treatment process by using the support vector machine algorithm to obtain the fault classification results;

[0064] In this step, the fuzzy logic control algorithm refers to a control method based on fuzzy set theory and fuzzy logic, which is used to process uncertain and inaccurate information. The support vector machine algorithm refers to a supervised learning method, which is used for classification and regression analysis and is especially suitable for high-precision classification of small sample data.

[0065] In this step, the fuzzy logic control algorithm can adjust the operating parameters such as the aeration volume and the chemical agent dosage according to the preset rules and the current water quality parameter values to optimize the treatment effect. For example, if the prediction result shows that the COD value is too high, the aeration volume or the chemical agent dosage can be increased. The support vector machine algorithm can establish a fault mode classification model by training historical fault data; when the real-time monitoring data is input into the model, it can identify whether there is a fault and its type at present, such as equipment failure, abnormal process parameters, etc.

[0066] Step 104: Based on the prediction result, the operation data, the optimized set values of the operating parameters, and the fault classification result, construct a comprehensive monitoring and management system based on the cloud platform. The comprehensive monitoring and management system integrates an expert system and a user-defined alarm rule function to realize the automatic monitoring of the sewage treatment process;

[0067] In this step, the comprehensive monitoring and management system refers to a platform that integrates various monitoring and management functions and is used for real-time monitoring and management of the sewage treatment process. The expert system refers to a computer system based on knowledge and reasoning, which is used to solve complex problems and provide decision support.

[0068] The comprehensive monitoring and management system constructed in this step can run on the cloud platform and display various monitoring data and prediction results in real time. The expert system can provide decision support according to the preset knowledge base, and the user-defined alarm rule function allows users to set specific alarm conditions. When the monitoring data exceeds the set threshold, the system will automatically send an alarm to notify relevant personnel.

[0069] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0070] By collecting and processing the water quality parameter values in real time, the system can provide continuous and stable monitoring data and timely discover and handle abnormal situations;

[0071] The dynamic model optimized by deep neural network and genetic algorithm improves the prediction accuracy and robustness, helps to take measures in advance to avoid water quality exceeding the standard;

[0072] The fuzzy logic control algorithm can dynamically adjust the operation parameters according to real-time data, optimize the treatment effect, and reduce energy consumption and chemical agent costs;

[0073] The support vector machine algorithm can effectively identify the fault modes, help to troubleshoot in time, and ensure the stable operation of the system;

[0074] The integrated monitoring and management system based on the cloud platform integrates the expert system and the user-defined alarm rule function, realizes the intelligent management and automatic monitoring of the sewage treatment process, and improves the management level and efficiency.

[0075] To achieve the intelligent management of the sewage treatment process and the timely diagnosis of faults, and improve the operation efficiency and reliability of the system. Based on this, the present invention provides a specific embodiment. In step 103, the fuzzy logic control algorithm is used to dynamically adjust the set value of the operation parameters of the sewage treatment system to which the sewage treatment facility belongs, and the optimized set value of the operation parameters is obtained. Based on the optimized set value of the operation parameters, the support vector machine algorithm is used to classify and identify the fault modes of the sewage treatment system during the sewage treatment process, and the fault classification result is obtained. The specific steps are as follows:

[0076] Step 301: Based on the prediction result and the operation data, collect the real-time second water quality parameter values and the set values of the operation parameters of the sewage treatment system to which the sewage treatment facility belongs to obtain real-time data;

[0077] This step collects the second water quality parameter values and the set values of the operation parameters in real time based on the prediction result and the operation data to form real-time data. The second water quality parameter values are such as pH value, dissolved oxygen, chemical oxygen demand, etc., and the set values of the operation parameters are such as aeration volume, chemical agent dosing ratio, etc.

[0078] Step 302: Based on the real-time data, set the input variables of the fuzzy logic control algorithm. The input variables include water quality parameters and operation parameters. The water quality parameters include pH value, dissolved oxygen, and chemical oxygen demand. The operation parameters include aeration volume and chemical agent dosing ratio;

[0079] This step takes the water quality parameters and the operation parameters as the input variables of the fuzzy logic control algorithm, laying the foundation for the next step of running the algorithm.

[0080] Step 303: Define the fuzzy rules, apply the fuzzy logic control algorithm, and perform fuzzy reasoning according to the input variables and the fuzzy rules to obtain the optimized set value of the operation parameters to optimize the sewage treatment effect;

[0081] In this step, the fuzzy rules define the relationship between the input variables and the output variables and are used to guide the fuzzy inference process. Fuzzy inference refers to the process of deriving the optimized operating parameter settings based on the input variables and the fuzzy rules.

[0082] In this step, fuzzy rules are defined. For example, when the pH value is low and the aeration rate is high, the aeration rate is reduced; when the dissolved oxygen is low and the chemical dosing ratio is high, the chemical dosing ratio is increased. Based on the defined fuzzy rules and the input variables, fuzzy inference is performed to calculate the optimal operating parameter settings; defuzzification methods, such as the centroid method, the maximum membership degree method, etc., are used to convert the fuzzy inference results into specific numerical values to obtain the optimized operating parameter settings.

[0083] Step 304: Train a support vector machine model based on the optimized operating parameter settings and the second water quality parameter value to identify and classify fault modes and obtain a fault classification result;

[0084] In this step, the optimized operating parameter settings and the second water quality parameter value are used as inputs to train a support vector machine model; through the trained support vector machine model, fault mode recognition and classification are performed on real-time data to obtain a fault classification result.

[0085] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0086] By collecting and processing key water quality parameters and operating parameters in real time, real-time monitoring of the sewage treatment process is realized to ensure timely adjustment of the treatment effect;

[0087] A dynamic model is constructed using a deep neural network and a genetic algorithm, and the operating parameters are dynamically adjusted in combination with a fuzzy logic control algorithm to optimize the sewage treatment effect and improve the treatment efficiency;

[0088] Fault modes in the treatment process are classified and identified through a support vector machine algorithm to detect and diagnose faults in a timely manner to ensure the stable operation of the system;

[0089] The functions of an expert system and user-defined alarm rules are integrated to realize automatic monitoring and intelligent management of the sewage treatment process, and improve the intelligent level and operating efficiency of the system.

[0090] The present invention provides a specific embodiment. In step 303, fuzzy rules are defined, a fuzzy logic control algorithm is applied, and based on the input variables and the fuzzy rules, fuzzy inference is performed to obtain optimized operating parameter settings to optimize the sewage treatment effect. The specific steps are as follows:

[0091] Step 311: Define fuzzy sets, and using membership functions, convert the second water quality parameter value and the operating parameter setting value in the input variables into the membership degrees of the fuzzy sets;

[0092] In this step, a fuzzy set refers to a mathematical tool for dealing with uncertainty and imprecise information, and each element has a membership degree value indicating the degree to which the element belongs to the set. A membership function refers to a function that defines the degree to which an element belongs to a fuzzy set, and its value range is usually from 0 to 1.

[0093] In this step, several fuzzy sets are defined for each input variable. For example, the pH value can be defined as three fuzzy sets: low, medium, and high; the dissolved oxygen can be defined as three fuzzy sets: low, moderate, and high; the chemical oxygen demand can be defined as three fuzzy sets: low, medium, and high; the aeration rate can be defined as three fuzzy sets: low, medium, and high; the chemical agent dosing ratio can be defined as three fuzzy sets: low, medium, and high; a membership function is defined for each fuzzy set. For example, the low fuzzy set of the pH value can use a triangular membership function; substitute the second water quality parameter value and the operating parameter setting value collected in real time into the corresponding membership function to calculate their membership degrees in each fuzzy set.

[0094] Step 312: Based on the fuzzy sets and membership degrees, define fuzzy rules;

[0095] When defining fuzzy rules in this step, the relationship between the input variables and the output variables needs to be considered. For example, Rule 1, if the pH value is low and the dissolved oxygen is low, then the aeration rate is high; Rule 2, if the chemical oxygen demand is high and the chemical agent dosing ratio is low, then the chemical agent dosing ratio is increased; Rule 3, if the pH value is moderate and the dissolved oxygen is moderate, then the aeration rate is moderate; Rule 4, if the chemical oxygen demand is moderate and the chemical agent dosing ratio is moderate, then the chemical agent dosing ratio is moderate.

[0096] Step 313: Apply the fuzzy logic control algorithm, perform fuzzy inference according to the fuzzy rules and the fuzzy sets, calculate the optimal operating parameter setting value, and process the optimal operating parameter setting value using a defuzzification method to obtain the optimized operating parameter setting value;

[0097] In this step, the defuzzification method refers to converting the result of fuzzy inference into a specific numerical value for practical application.

[0098] This step performs fuzzy inference based on the defined fuzzy rules and the membership degrees of the input variables. For example, if the current pH value is 5.5, the dissolved oxygen is 1.8 mg / L, the chemical oxygen demand is 600 mg / L, and the chemical dosing ratio is 0.5%, then according to Rule 1 and Rule 2, it can be concluded that the aeration volume should be high and the chemical dosing ratio should be high; convert the results of the fuzzy inference into specific numerical values. Commonly used defuzzification methods include the centroid method, the maximum membership degree method, etc. For example, use the centroid method to calculate the optimal value of the aeration volume.

[0099] More specifically, the embodiment of the present invention also provides a formula for calculating the optimal operating parameter setting value. The specific calculation formula is as follows:

[0100] ;

[0101] Wherein, is the optimized operating parameter setting value at the current time point ; is the number of input variables; is the th weight of the th input variable at time is the th water quality parameter value at the current time point ; is the th operating parameter setting value at the current time point ; is the fuzzy inference function for calculating the contribution of the th input variable to the optimal operating parameter setting value; is the time window function;

[0102] This formula comprehensively considers the fuzzy inference function, the time window function, and the adaptive weight adjustment function, better reflecting the actual situation and improving the accuracy and robustness of the optimization of the operating parameter setting value.

[0103] Wherein, the calculation formula of the fuzzy inference function is as follows:

[0104] ;

[0105] Wherein, is the fuzzy inference function; is the th membership degree of the th water quality parameter value at the current time point is the th membership degree of the th operating parameter setting value at the current time point It is a time window function used to consider the trend of historical data and the weight of current data;

[0106] This fuzzy inference function flexibly adjusts the output value according to different input variables and fuzzy rules to meet the optimization requirements under different working conditions. At the same time, this function can handle uncertainty and nonlinear problems, improving the robustness and adaptability of the system.

[0107] Among them, the calculation formula of the time window function is as follows:

[0108] ;

[0109] Among them, is the time window function; is the influence factor of historical data, and its value range is , which is used to balance the weights of historical data and current data; is the decay factor, which is used to control the decay rate of the influence of historical data; is the current time point, which is used to calculate the influence of the data at the current time point on the optimization result; is the reference time point, which is used to calculate the influence of historical data on the current optimization result; is the adaptive weight adjustment function, which is used to dynamically adjust the weight according to the fluctuation of current data;

[0110] This time window function takes into account the influence of historical data on the current optimization result. The influence of historical data gradually weakens over time, which helps to maintain the dynamic adaptability of the model. At the same time, it emphasizes the importance of current data, which helps the model to quickly respond to current changes and improve real-time performance.

[0111] Among them, the calculation formula of the adaptive weight adjustment function is as follows:

[0112] ;

[0113] Among them, is the fluctuation sensitivity factor, which is used to control the sensitivity of the weight to data fluctuations; is the historical average value of the th water quality parameter value; is the th water quality parameter value at the current time point ;

[0114] This adaptive weight adjustment function dynamically adjusts the weight according to the deviation between the current data and the historical average value. When the data fluctuates greatly, the weight will decrease, avoiding the deviation of the optimization result caused by abnormal data, enabling the model to dynamically adjust according to the actual situation, and improving the robustness and accuracy of the optimization.

[0115] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0116] Through the fuzzy logic control algorithm, the set values of the operating parameters of the sewage treatment system are adjusted and optimized in real time, improving the treatment effect and system stability;

[0117] The fuzzy logic control algorithm can handle uncertain and imprecise information, making the control more flexible and precise;

[0118] By optimizing the operating parameters, the occurrence of system failures is reduced, improving the reliability and safety of the system;

[0119] The optimized set values of the operating parameters can reduce unnecessary aeration volume and chemical dosage, reducing energy consumption and chemical costs, and achieving energy conservation and emission reduction;

[0120] Combining fuzzy logic control and defuzzification methods, the intelligent management of the sewage treatment process is realized, improving the automation level and management level of the system.

[0121] To achieve the comprehensive automatic monitoring and management of the sewage treatment process and ensure the efficient and stable operation of the sewage treatment process, based on this, the present invention provides a specific embodiment. In step 104, based on the prediction result, the operation data, the optimized set value of the operating parameter, and the fault classification result, a comprehensive monitoring and management system based on the cloud platform is constructed. The comprehensive monitoring and management system integrates an expert system and a user-defined alarm rule function to realize the automatic monitoring of the sewage treatment process, specifically including the following steps:

[0122] Step 401: Integrate and clean the data of the prediction result, the operation data, the optimized set value of the operating parameter, and the fault classification result to obtain sewage treatment data;

[0123] In this step, the prediction result, the operation data, the optimized set value of the operating parameter, and the fault classification result are merged into a unified data set to obtain sewage treatment data. For example, database or data warehouse technology can be used to store these data in a table; the integrated data is cleaned, including removing duplicate data, correcting incorrect data, filling in missing values, etc. For example, SQL queries and data cleaning tools can be used to complete these tasks. Suppose the pH value of a certain record is negative, which is obviously incorrect and needs to be corrected or deleted.

[0124] Step 402: Based on the sewage treatment data, use the front-end display technology of the cloud platform to display the state and prediction trend of sewage treatment in real time to provide a monitoring interface;

[0125] In this step, the front-end display technology refers to the technology used to display data in real time on the user interface.

[0126] This step uses the front-end display technology of the cloud platform and combines the APIs provided by the cloud platform to achieve the display of real-time data, so as to provide a user-friendly monitoring interface, showing the current water quality parameter values, optimized operating parameter setting values, prediction results, and fault classification results. For example, chart libraries such as ECharts or D3.js can be used to draw real-time water quality parameter curve charts and prediction trend charts. For example, there can be a dashboard on the monitoring interface to display real-time data such as pH value, dissolved oxygen, and chemical oxygen demand, and another area to display the predicted trend chart.

[0127] Step 403: Integrate an expert system, which combines the target expert knowledge base to provide the optimal operation strategy corresponding to the state of sewage treatment;

[0128] In this step, the target expert knowledge base refers to a database containing expert experience and knowledge, which is used to guide the decision-making of the expert system.

[0129] This step integrates a rule-based expert system, which can provide the optimal operation strategy according to the current water quality parameters and operating parameters. For example, if the pH value is too low, the system recommends increasing the chemical dosing ratio; this system combines a database containing expert experience and knowledge, which is used to guide the decision-making of the expert system. For example, the knowledge base can contain treatment methods and optimization strategies for various fault modes.

[0130] Step 404: Generate a user interface to enable users to set custom alarm rules according to actual needs and the user-defined alarm rule function. The custom alarm rules include different thresholds and alarm conditions. When the second water quality parameter value or the optimized operating parameter setting value in the real-time data exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and processing;

[0131] This step generates a user-friendly interface that allows users to set custom alarm rules. For example, users can set the threshold of the pH value to 6 - 8, and if the pH value exceeds this range, the system will trigger an alarm; users can set different thresholds and alarm conditions. For example, users can set an alarm to be triggered when the dissolved oxygen is lower than 2 mg / L, or when the aeration volume exceeds 80 m³ / h. These rules can be configured through the interface and saved to the database.

[0132] Step 405: Based on the sewage treatment data, monitoring interface, expert system, and user interface, build a comprehensive monitoring and management system based on the cloud platform to achieve automatic monitoring of sewage treatment;

[0133] In this step, the integrated monitoring and management system refers to a platform that integrates various monitoring and management functions and is used to monitor and manage the sewage treatment process in real time.

[0134] This step integrates all the above functions into a cloud-based platform system. This system can monitor the status of sewage treatment in real time, provide predictive trends, perform optimization operations according to the suggestions of the expert system, and trigger alarms according to the alarm rules set by the user. For example, the system can be deployed on the cloud platform and utilize cloud servers and database services to achieve data storage and processing; the system can automatically collect and process real-time data, operate according to preset rules and strategies, and automatically trigger alarms when abnormalities occur to ensure the efficient and stable operation of the sewage treatment process.

[0135] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0136] By displaying the status and predictive trends of sewage treatment in real time, users can understand the operation of the system at any time, and discover and handle abnormalities in a timely manner;

[0137] The expert system combines the target expert knowledge base to provide the optimal operation strategy, helping users optimize the operation parameters and improve the treatment effect and system stability;

[0138] Users can set custom alarm rules according to actual needs, and automatically trigger alarms when the data exceeds the preset range to achieve rapid response and handling;

[0139] The integrated monitoring and management system integrates various functions, realizes the intelligent management and automatic monitoring of the sewage treatment process, and improves the automation level and management level of the system;

[0140] Through data integration and cleaning, ensure the accuracy and consistency of data, provide reliable data support for decision-making, and improve the reliability and efficiency of the system.

[0141] To make full use of expert experience and knowledge, guide decision-making and operation in the sewage treatment process, and ensure the stable operation and optimal performance of the system. The present invention provides a specific embodiment. In step 403, an expert system is integrated. The expert system combines the target expert knowledge base to provide the optimal operation strategy corresponding to the status of sewage treatment, which specifically includes the following steps:

[0142] Step 411: Formulate fault diagnosis rules based on historical data, where the historical data includes the first water quality parameter values;

[0143] In this step, historical data refers to the water quality parameter values and other relevant data collected in the past time period and is used for analysis and modeling.

[0144] This step collects water quality parameter values over a past period, including pH value, dissolved oxygen, chemical oxygen demand, etc., as well as other relevant data, such as operating parameter setting values, fault records, etc.; analyzes the historical data to find out the characteristics and patterns related to faults. For example, if the pH value continuously drops below 6 and the dissolved oxygen is lower than 2 mg / L, it may indicate a fault in the aeration system. These patterns can be transformed into fault diagnosis rules. For example, if the pH value < 6 and the dissolved oxygen < 2 mg / L, then it is judged that there is a fault in the aeration system.

[0145] Step 412: Based on the fault classification result and the fault diagnosis rules, formulate known optimal operation strategies for different fault types;

[0146] This step combines the fault diagnosis rules and the fault classification result to formulate the optimal operation strategy for each fault type. For example, for a fault in the aeration system, the optimal operation strategy may be to increase the aeration volume to 80 m³ / h and check the aeration equipment; for a fault in the chemical dosing system, the optimal operation strategy may be to increase the chemical dosing ratio to 0.8% and check the chemical dosing equipment.

[0147] Step 413: Based on the fault diagnosis rules and the known optimal operation strategies, construct an initial expert knowledge base, introduce an adaptive learning mechanism, and optimize the expert knowledge base to obtain a target expert knowledge base;

[0148] In this step, the adaptive learning mechanism refers to the mechanism that optimizes the expert knowledge base through continuous learning and updating.

[0149] This step integrates the fault diagnosis rules and the optimal operation strategies into a database to form an initial expert knowledge base. For example, the knowledge base may contain the following entries: the fault type is a fault in the aeration system, the diagnosis rule is that the pH value < 6 and the dissolved oxygen < 2 mg / L; increase the aeration volume to 80 m³ / h and check the aeration equipment. By continuously learning new fault data and operation results, the expert knowledge base is optimized. For example, after each fault occurs, the system records the actual operation results and effects. If a certain operation strategy has poor effects, the system can automatically adjust or add new rules. This adaptive learning mechanism can gradually improve the accuracy and practicality of the knowledge base.

[0150] Target expert knowledge base: The expert knowledge base optimized by the adaptive learning mechanism, which has higher accuracy and practicality. For example, the optimized knowledge base may contain more detailed fault diagnosis rules and more effective operation strategies.

[0151] Step 414: Based on the target expert knowledge base, determine the optimal operation strategy corresponding to the state of the sewage treatment;

[0152] This step uses an optimized target expert knowledge base to match the corresponding fault types and optimal operation strategies according to the current water quality parameter values and operation parameter setting values; when the system detects a certain fault type, according to the rules in the target expert knowledge base, it provides the corresponding optimal operation strategy. For example, if the current pH value is 5.5 and the dissolved oxygen is 1.8 mg / L, the system determines that there is a fault in the aeration system, and according to the optimal operation strategy in the knowledge base, it is recommended to increase the aeration volume to 80 m³ / h and check the aeration equipment.

[0153] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0154] The fault diagnosis rules formulated through historical data can more accurately identify and classify fault types, improving the accuracy of fault diagnosis;

[0155] The optimal operation strategies formulated by combining expert experience and historical data can provide targeted solutions, improving the treatment effect and stability of the system;

[0156] Introducing an adaptive learning mechanism to continuously optimize the expert knowledge base enables the system to adapt to new fault types and operation requirements, improving the intelligence level of the system;

[0157] Based on the target expert knowledge base, the system can provide optimal operation strategies in real time, respond to and handle faults in a timely manner, ensuring the efficient and stable operation of the sewage treatment process;

[0158] By means of a data-driven method, optimizing fault diagnosis and operation strategies can improve the reliability and efficiency of the system, reduce human intervention, and lower operating costs.

[0159] To enable users to discover and handle abnormal situations in a timely manner and ensure the efficient and stable operation of the sewage treatment process, based on this, the present invention provides a specific embodiment. In step 404, a user interface is generated so that the user can set custom alarm rules according to actual needs and the user-defined alarm rule function. The custom alarm rules include different thresholds and alarm conditions. When the second water quality parameter value or the optimized operation parameter setting value in the real-time data exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and handling, which specifically includes the following steps:

[0160] Step 421: Generate a user interface so that the user can set custom alarm rules according to actual needs and the user-defined alarm rule function. The custom alarm rules include different thresholds and alarm conditions;

[0161] In this step, the threshold refers to the set upper and lower limit values, and an alarm is triggered when the data exceeds this range. The alarm condition refers to the specific condition for triggering the alarm, such as a certain water quality parameter value exceeding the threshold.

[0162] This step generates a user-friendly interface, including the function of setting custom alarm rules. The interface is clear and intuitive, facilitating user operation. Users can set different thresholds and alarm conditions on the interface. For example, users can set the threshold of pH value to 6 - 8. If the pH value exceeds this range, the system will trigger an alarm. Users can also set the threshold of dissolved oxygen to 2 - 8 mg / L. If the dissolved oxygen is lower than 2 mg / L or higher than 8 mg / L, the system will also trigger an alarm. The alarm rules set by users can be saved in the database for the system to call in real time.

[0163] Step 422: Based on the custom alarm rules, when the value of the second water quality parameter or the optimized operating parameter setting value in the real-time data exceeds the corresponding preset range, trigger an alarm, notify the user in real time through multiple notification channels, and generate real-time alarm information.

[0164] In this step, real-time alarm information refers to the alarm information generated by the system when the alarm condition is met, including the alarm time, alarm reason, etc.

[0165] This step monitors the value of the second water quality parameter and the optimized operating parameter setting value in real time, such as pH value, dissolved oxygen, chemical oxygen demand, aeration volume, chemical agent dosing ratio, etc. When the real-time data exceeds the threshold set by the user, the system automatically triggers an alarm. For example, if the pH value is 5.5, which is lower than the set threshold of 6, the system will trigger an alarm. Notify the user in real time through multiple notification channels, such as text messages, emails, APP push, etc. For example, the system can send a text message with the content "Attention, the pH value is 5.5, lower than the set threshold of 6. Please check and process." The system generates real-time alarm information, including the alarm time, alarm reason, current water quality parameter value, etc. For example, the alarm information may include the alarm time 2024 - 11 - 21 15:30, the alarm reason that the pH value is lower than the threshold, and the current pH value of 5.5.

[0166] Step 423: Based on the real-time alarm information, select the corresponding rapid response mechanism and the optimal operation strategy to achieve real-time response and processing.

[0167] In this step, the rapid response mechanism refers to the predefined emergency measures for dealing with alarms, such as automatically adjusting operating parameters, notifying maintenance personnel, etc.

[0168] After receiving real-time alarm information, this step analyzes the alarm reasons and the current status. For example, if the alarm reason is that the pH value is lower than the threshold, search for the corresponding quick response mechanism and the optimal operation strategy; according to the alarm information, select the appropriate quick response mechanism. For example, if the pH value is lower than the threshold, automatically adjust the chemical dosing ratio and increase the chemical dosing amount; combine with the target expert knowledge base and apply the optimal operation strategy. For example, according to the rules in the expert knowledge base, increase the chemical dosing ratio to 0.8% and check the chemical dosing equipment; execute the selected operation strategy, such as adjusting the chemical dosing ratio, and record the operation result. At the same time, notify the maintenance personnel for further inspection and handling.

[0169] The embodiments of the present invention can achieve the beneficial effects through the above steps as follows:

[0170] By setting custom alarm rules through the user interface, the system can monitor water quality parameters and operation parameters in real time and detect abnormal situations in a timely manner;

[0171] Through multiple notification channels, notify users in real time to ensure that users can learn the alarm information in the first time and take measures in a timely manner;

[0172] Based on real-time alarm information, the system can select appropriate quick response mechanisms and optimal operation strategies to achieve quick response and processing and reduce the impact of failures;

[0173] Combined with the target expert knowledge base, the system can provide the best operation suggestions, improve the intelligent management level of the system, reduce human intervention, and improve the processing efficiency;

[0174] Through a data-driven method, optimize alarm rules and operation strategies to improve the reliability and efficiency of the system and reduce operating costs.

[0175] The present invention provides a specific embodiment. In step 102, data processing is performed on the first water quality parameter value, and based on the processed first water quality parameter value, a dynamic model of the sewage treatment process is constructed using a deep neural network, and a genetic algorithm is introduced to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model. The optimized dynamic model is used to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility, which specifically includes the following steps:

[0176] Step 201: Perform data normalization processing on the first water quality parameter value, extract key information from the normalized data to obtain the processed first water quality parameter value, and based on the processed first water quality parameter value, construct a dynamic model of the sewage treatment process using a deep neural network. Use a genetic algorithm to adjust the weights, biases, the number of layers of the neural network, and the number of neurons in each layer to optimize the structure and parameters of the dynamic model to obtain a preliminarily optimized dynamic model;

[0177] In this step, the weight refers to the parameter connecting two neurons in the neural network, representing the importance of the input signal. The bias refers to an additional parameter for each neuron in the neural network, which is used to adjust the position of the activation function.

[0178] This step performs data normalization on the first water quality parameter value, converting the first water quality parameter value to the range of 0 to 1. For example, the min-max normalization method can be used; valuable features for model training and prediction are extracted from the normalized data to obtain the processed first water quality parameter value; for example, principal component analysis (PCA) can be used to extract the main features, or features highly correlated with the target variable can be selected. Based on the processed first water quality parameter value, a dynamic model of the sewage treatment process is constructed using a deep neural network. For example, a multi-layer perceptron (MLP) is used. Assuming the model structure is an input layer, two hidden layers, and an output layer, the number of nodes in the input layer is the number of extracted features, and the number of nodes in the output layer is the predicted water quality parameter; the genetic algorithm is used to optimize the weights, biases, number of layers, and number of neurons in each layer of the model. The genetic algorithm searches for the optimal solution through operations such as crossover and mutation. For example, the initial population size can be set to 100, the crossover probability to 0.8, the mutation probability to 0.1, and the number of iterations to 100 times; the dynamic model optimized by the genetic algorithm has better prediction performance. For example, the optimized model may have fewer layers and a more reasonable number of neurons, and the weights and biases are also optimized.

[0179] Step 202: Use the processed first water quality parameter value to train the preliminarily optimized dynamic model to obtain an optimized dynamic model, and use the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility;

[0180] This step uses the processed first water quality parameter value to train the preliminarily optimized dynamic model. During the training process, the gradient descent method (such as the Adam optimizer) is used to adjust the model parameters until the loss function converges; for example, the mean square error (MSE) can be used as the loss function; the trained dynamic model has higher prediction accuracy and robustness. For example, the trained model can more accurately predict future water quality parameter values; use the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facility. For example, the water quality parameter values such as pH value, dissolved oxygen, and chemical oxygen demand at a future moment can be predicted, as well as the current operation data such as aeration volume and chemical dosage.

[0181] The embodiments of the present invention can achieve the beneficial effects as follows through the above steps:

[0182] By performing data normalization on the first water quality parameter values, the influence of different dimensions is eliminated, the consistency and comparability of the data are improved, which is beneficial to the training and prediction of the model;

[0183] Extract key information from the normalized data, reduce redundant data, and improve the training efficiency and prediction accuracy of the model;

[0184] Adopt a deep neural network to construct a dynamic model, which can learn and model complex non-linear relationships and improve the prediction ability of the model;

[0185] Optimize the structure and parameters of the model through a genetic algorithm, improve the prediction accuracy and robustness of the model, and reduce the risk of overfitting;

[0186] Use the optimized dynamic model to predict the sewage treatment effect, which can provide future water quality parameter values and operation data in real time, helping managers to adjust operation parameters in a timely manner to ensure the sewage treatment effect.

[0187] Figure 2 The structural schematic diagram of a monitoring system for the sewage treatment progress is provided for the embodiments of the present invention, as Figure 2 shown, the system includes:

[0188] A collection module 21 for collecting the first water quality parameter values of key nodes of sewage treatment facilities within a historical time period;

[0189] An optimization module 22 for performing data processing on the first water quality parameter values, and based on the processed first water quality parameter values, constructing a dynamic model of the sewage treatment process using a deep neural network, and introducing a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and using the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facilities;

[0190] An identification module 23 for dynamically adjusting the set value of the operation parameters of the sewage treatment system to which the sewage treatment facilities belong using a fuzzy logic control algorithm to obtain an optimized set value of the operation parameters, and based on the optimized set value of the operation parameters, classifying and identifying the fault modes of the sewage treatment system during the sewage treatment process using a support vector machine algorithm to obtain a fault classification result;

[0191] A construction module 24 for constructing a comprehensive monitoring and management system based on a cloud platform based on the prediction result, the operation data, the optimized set value of the operation parameters, and the fault classification result, and the comprehensive monitoring and management system integrates an expert system and a user-defined alarm rule function to realize the automatic monitoring of the sewage treatment process.

[0192] Figure 2The described sewage treatment progress monitoring system can execute Figure 1 the sewage treatment progress monitoring method described in the illustrated embodiment. Its implementation principle and technical effects will not be elaborated further. For the sewage treatment progress monitoring system in the above embodiment, the specific ways in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0193] In a possible design, Figure 2 the sewage treatment progress monitoring system of the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, the computing device can include a storage component 31 and a processing component 32;

[0194] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are for the processing component 32 to call and execute.

[0195] The processing component 32 is used to: collect the first water quality parameter values of the key nodes of the sewage treatment facilities in the historical time period; perform data processing on the first water quality parameter values, and based on the processed first water quality parameter values, construct a dynamic model of the sewage treatment process using a deep neural network, and introduce a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, use the optimized dynamic model to predict the sewage treatment effect to obtain a prediction result and the operation data of the sewage treatment facilities; use a fuzzy logic control algorithm to dynamically adjust the setting values of the operation parameters of the sewage treatment system to which the sewage treatment facilities belong to obtain optimized operation parameter setting values, and based on the optimized operation parameter setting values, classify and identify the fault modes of the sewage treatment system during the sewage treatment process using a support vector machine algorithm to obtain a fault classification result; based on the prediction result, the operation data, the optimized operation parameter setting values, and the fault classification result, construct a cloud platform-based integrated monitoring and management system, and the integrated monitoring and management system integrates an expert system and a user-defined alarm rule function to achieve automatic monitoring of the sewage treatment process.

[0196] Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0197] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0198] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0199] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module may be an output device, an input device, etc.

[0200] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0201] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0202] The embodiment of the present invention also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above-mentioned Figure 1 monitoring method for the sewage treatment progress shown in the embodiment.

[0203] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0204] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0205] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0206] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the progress of sewage treatment, characterized in that: include: Collect the first water quality parameter values ​​of key nodes of sewage treatment facilities in a historical time period; Performing data processing on the first water quality parameter value, and based on the processed first water quality parameter value, using a deep neural network to construct a dynamic model of the sewage treatment process, and introducing a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and using the optimized dynamic model to predict the sewage treatment effect, to obtain a prediction result and operation data of the sewage treatment facility; Dynamically adjust the operating parameter setting values ​​of the sewage treatment system of the sewage treatment facility by using a fuzzy logic control algorithm to obtain optimized operating parameter setting values, and classify and identify the failure modes of the sewage treatment system during the sewage treatment process by using a support vector machine algorithm based on the optimized operating parameter setting values ​​to obtain a failure classification result; Among them, the fuzzy logic control algorithm adopts the following formula: ； in, At the current time Optimized operating parameter setting values; is the number of input variables; It is Input variables at time The weight of It is The water quality parameter value at the current time point The value of It is The operating parameter setting value at the current time point The value of is a fuzzy inference function used to calculate the The contribution of each input variable to the optimal operating parameter setting value; is a time window function; Based on the prediction results, the operating data, the optimized operating parameter setting values ​​and the fault classification results, a comprehensive monitoring and management system based on a cloud platform is constructed. The comprehensive monitoring and management system integrates expert system and user-defined alarm rule functions to realize automatic monitoring of the sewage treatment process.

2. The method according to claim 1, characterized in that: The fuzzy logic control algorithm is used to dynamically adjust the operating parameter setting values ​​of the sewage treatment system to which the sewage treatment facility belongs, to obtain optimized operating parameter setting values, and based on the optimized operating parameter setting values, the support vector machine algorithm is used to classify and identify the failure mode of the sewage treatment system during the sewage treatment process, to obtain a failure classification result, including: Based on the prediction result and the operation data, collecting the real-time second water quality parameter value and the operation parameter setting value of the sewage treatment system to which the sewage treatment facility belongs to obtain real-time data; Based on the real-time data, setting input variables of the fuzzy logic control algorithm, the input variables including water quality parameters and operating parameters, the water quality parameters including pH value, dissolved oxygen and chemical oxygen demand, the operating parameters including aeration volume and reagent dosage ratio; Defining fuzzy rules, applying fuzzy logic control algorithms, and performing fuzzy reasoning according to the input variables and the fuzzy rules to obtain optimized operating parameter setting values ​​to optimize the sewage treatment effect; A support vector machine model is trained based on the optimized operating parameter setting value and the second water quality parameter value to identify and classify fault modes and obtain a fault classification result.

3. The method according to claim 2, characterized in that The defining of fuzzy rules, applying fuzzy logic control algorithms, and performing fuzzy reasoning according to the input variables and the fuzzy rules to obtain optimized operating parameter setting values ​​to optimize the sewage treatment effect include: Define a fuzzy set, and use a membership function to convert the second water quality parameter value and the operating parameter setting value in the input variable into the membership of the fuzzy set; Based on the fuzzy sets and membership degrees, defining fuzzy rules; A fuzzy logic control algorithm is applied to perform fuzzy reasoning according to the fuzzy rules and the fuzzy sets to calculate the optimal operating parameter setting values, and a defuzzification method is used to process the optimal operating parameter setting values ​​to obtain optimized operating parameter setting values.

4. The method according to claim 2, characterized in that: Based on the prediction results, the operation data, the optimized operation parameter setting values ​​and the fault classification results, a comprehensive monitoring and management system based on a cloud platform is constructed, and the comprehensive monitoring and management system integrates expert system and user-defined alarm rule functions to realize automatic monitoring of the sewage treatment process, including: Performing data integration and data cleaning on the prediction results, the operation data, the optimized operation parameter setting values, and the fault classification results to obtain sewage treatment data; Based on the sewage treatment data, the front-end display technology of the cloud platform is used to display the status and forecast trend of sewage treatment in real time to provide a monitoring interface; An integrated expert system, wherein the expert system combines a target expert knowledge base to provide an optimal operation strategy corresponding to the state of the sewage treatment; Generate a user interface to enable the user to set a custom alarm rule according to actual needs and the user-defined alarm rule function, wherein the custom alarm rule includes different thresholds and alarm conditions, and when the second water quality parameter value in the real-time data or the optimized operating parameter setting value exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and processing; Based on the sewage treatment data, monitoring interface, expert system and user interface, a comprehensive monitoring and management system based on a cloud platform is constructed to realize automatic monitoring of sewage treatment.

5. The method according to claim 4, characterized in that The integrated expert system, which combines the target expert knowledge base to provide an optimal operation strategy corresponding to the state of sewage treatment, includes: Formulate a fault diagnosis rule based on historical data, wherein the historical data includes a first water quality parameter value; Based on the fault classification results and the fault diagnosis rules, formulating known optimal operation strategies for different fault types; Based on the fault diagnosis rules and the known optimal operation strategy, an initial expert knowledge base is constructed, an adaptive learning mechanism is introduced, the expert knowledge base is optimized, and a target expert knowledge base is obtained; An optimal operation strategy corresponding to the state of sewage treatment is determined based on the target expert knowledge base.

6. The method according to claim 4, characterized in that The user interface is generated so that the user can set a custom alarm rule according to actual needs and the user-defined alarm rule function. The custom alarm rule includes different thresholds and alarm conditions. When the second water quality parameter value in the real-time data or the optimized operating parameter setting value exceeds the corresponding preset range, an alarm is triggered to achieve real-time response and processing, including: Generate a user interface to enable the user to set a custom alarm rule according to actual needs and the user-defined alarm rule function, wherein the custom alarm rule includes different thresholds and alarm conditions; Based on the custom alarm rules, when the second water quality parameter value in the real-time data or the optimized operating parameter setting value exceeds the corresponding preset range, an alarm is triggered, and the user is notified in real time through multiple notification channels, and real-time alarm information is generated; Based on the real-time alarm information, a corresponding rapid response mechanism and the optimal operation strategy are selected to achieve real-time response and processing.

7. The method according to claim 1, characterized in that The data processing is performed on the first water quality parameter value, and based on the processed first water quality parameter value, a dynamic model of the sewage treatment process is constructed using a deep neural network, and a genetic algorithm is introduced to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and the optimized dynamic model is used to predict the sewage treatment effect to obtain a prediction result and operation data of the sewage treatment facility, including: Performing data normalization processing on the first water quality parameter value, and extracting key information from the normalized data to obtain the processed first water quality parameter value, and based on the processed first water quality parameter value, using a deep neural network to build a dynamic model of the sewage treatment process, and using a genetic algorithm to adjust the weights, biases, the number of layers of the neural network, and the number of neurons in each layer of the dynamic model to optimize the structure and parameters of the dynamic model, and obtain a preliminarily optimized dynamic model; The first water quality parameter value after treatment is used to train the preliminary optimized dynamic model to obtain an optimized dynamic model, and the optimized dynamic model is used to predict the sewage treatment effect to obtain the prediction result and the operation data of the sewage treatment facility.

8. A sewage treatment progress monitoring system, characterized in that: include: A collection module, used to collect the first water quality parameter values ​​of key nodes of the sewage treatment facility within a historical time period; an optimization module, for performing data processing on the first water quality parameter value, and based on the processed first water quality parameter value, using a deep neural network to construct a dynamic model of the sewage treatment process, and introducing a genetic algorithm to optimize the structure and parameters of the dynamic model to obtain an optimized dynamic model, and using the optimized dynamic model to predict the sewage treatment effect, and obtain a prediction result and operation data of the sewage treatment facility; an identification module, for dynamically adjusting the operating parameter setting values ​​of the sewage treatment system of the sewage treatment facility by using a fuzzy logic control algorithm to obtain optimized operating parameter setting values, and classifying and identifying the failure modes of the sewage treatment system during the sewage treatment process by using a support vector machine algorithm based on the optimized operating parameter setting values ​​to obtain a failure classification result; Among them, the fuzzy logic control algorithm adopts the following formula: ； in, At the current time Optimized operating parameter setting values; is the number of input variables; It is Input variables at time The weight of It is The water quality parameter value at the current time point The value of It is The operating parameter setting value at the current time point The value of is a fuzzy inference function used to calculate the The contribution of each input variable to the optimal operating parameter setting value; is a time window function; A construction module is used to construct a comprehensive monitoring and management system based on a cloud platform based on the prediction results, the operating data, the optimized operating parameter setting values ​​and the fault classification results. The comprehensive monitoring and management system integrates expert system and user-defined alarm rule functions to realize automatic monitoring of the sewage treatment process.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for monitoring the progress of sewage treatment as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a method for monitoring the progress of sewage treatment as described in any one of claims 1 to 7 is implemented.

Images