A water quality change monitoring system for sewage treatment
Through multi-parameter sensors and artificial intelligence algorithms, dynamically adjust data acquisition frequency, predict water quality changes, and optimize sewage treatment processes, the problem of inability to respond to water quality changes in real time in the existing technology is solved, the efficiency and accuracy of sewage treatment are improved, and real-time Monitoring and optimization.
Patent Information
- Application Number
- CN202410879010.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-07-02
AI Technical Summary
The existing sewage treatment monitoring system cannot respond to water quality changes in real time, and lacks dynamic data collection and adjustment and accurate prediction of water quality compliance time, resulting in insufficient treatment efficiency and resource optimization.
Using multi-parameter sensor monitoring module, adaptive data acquisition module, water quality monitoring module, optimization module and visualization module, dynamically adjust data acquisition frequency through artificial intelligence algorithms and machine learning models, predict water quality change trends, optimize sewage treatment process parameters, and provide Real-time data display and early warning information.
It improves monitoring efficiency and response speed, ensures the flexibility and accuracy of the sewage treatment process, improves the quality of the effluent water, promptly warning and decision-making support, and enhances user interaction experience.
Smart Images

Figure CN118409064B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of water quality monitoring, and in particular to a water quality change monitoring system for sewage treatment. Background Art
[0002] With the rapid development of industrialization and urbanization, water pollution is becoming increasingly serious, and sewage treatment has become an important part of environmental protection. Traditional sewage treatment methods mainly rely on physical, chemical and biological technologies. Although these technologies can remove pollutants in sewage to a certain extent, they have problems such as low treatment efficiency, high cost and complex operation. In addition, water quality monitoring in traditional sewage treatment mainly adopts manual sampling and laboratory analysis. This method is time-consuming and labor-intensive, and cannot achieve real-time monitoring of water quality changes, and it is difficult to meet the needs of modern sewage treatment for efficient and accurate monitoring.
[0003] In order to improve the efficiency of sewage treatment and the real-time monitoring, some automated water quality monitoring systems have been developed and applied. These systems can monitor different water quality parameters in sewage by integrating multiple sensors. However, most of these systems use fixed-frequency data collection methods, lack real-time analysis and prediction of water quality trends, and cannot dynamically adjust the monitoring frequency and treatment process according to the real-time changes in water quality. Therefore, there are limitations in treatment efficiency and resource optimization.
[0004] In addition, existing sewage treatment monitoring systems also have deficiencies in data processing and analysis. They usually lack efficient data models to predict water quality trends and are difficult to warn of potential abnormalities. At the same time, the information provided by the system is mostly a simple display of raw data, lacking in-depth data analysis and decision support, making it difficult for operators to grasp the water quality status in a timely and accurate manner and make corresponding adjustments.
[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention
[0006] The purpose of the present invention is to solve the problems that the existing sewage treatment monitoring system cannot respond to water quality changes in real time, lacks dynamic data collection and adjustment, and accurately predicts the time when water quality reaches the standard, and proposes a water quality change monitoring system for sewage treatment.
[0007] The purpose of the present invention can be achieved through the following technical solutions:
[0008] A water quality change monitoring system for sewage treatment, comprising:
[0009] Multi-parameter sensor monitoring module, used to monitor different parameters of water quality in the sewage treatment process through different sensors;
[0010] Adaptive data collection module: According to the analysis results of the artificial intelligence algorithm, the data collection frequency is dynamically adjusted to meet the real-time needs of water quality changes. The specific steps are as follows:
[0011] In the initial stage, water quality parameter data is collected through the multi-parameter sensor monitoring module at a preset fixed frequency, and then the collected raw data is cleaned, including noise removal, missing value filling and data standardization;
[0012] Extract useful features from raw data, including trends, seasonal patterns, and periodic changes in water quality parameters, and use machine learning algorithms to build data models to predict trends and potential anomalies in water quality parameters;
[0013] Input the real-time collected data into the data model for immediate analysis to obtain the current water quality status prediction. Use the adaptive algorithm to dynamically adjust the data collection frequency according to the prediction results of the data model and the preset logical rules. Specifically, the influence judgment value is obtained by comprehensively evaluating and analyzing the water quality change speed through the obtained measurement parameters, and this influence judgment value is used as the standard for measuring water quality changes.
[0014] The obtained shadow judgment value is compared with several preset shadow judgment value intervals, and different monitoring and adjustment frequencies are set corresponding to the several shadow judgment value intervals. When the shadow judgment value interval to which the shadow judgment value belongs is determined, the monitoring data is obtained at the current moment according to the corresponding monitoring and adjustment frequency;
[0015] Water quality monitoring module, used to analyze data detected by different sensors and predict the time when water quality reaches the standard;
[0016] An optimization module, which is used to improve the water quality optimization speed of sewage treatment through optimization steps;
[0017] The visualization module is used to provide a visual interface for real-time data display, historical data analysis, warning information and processing suggestions, which is convenient for operators to monitor and manage.
[0018] Furthermore, the shadow judgment value analysis process in the adaptive data acquisition module is as follows:
[0019] The measurement parameters include: instantaneous rate of change of water quality, average rate of change, Sen slope and time series analysis parameters, wherein the time series analysis parameters are obtained by obtaining the autoregressive coefficient in the time series model to obtain the absolute value of the autoregressive coefficient. The larger the absolute value of the autoregressive coefficient, the stronger the influence of the current value on the future value.
[0020] Then the instantaneous rate of change, average rate of change, Sen slope and absolute value of autoregressive coefficient are calibrated as ss, pb, sn and hg respectively, and after normalization, they are entered into the following formula: To get the shadow judgment value YPZ, where They are the preset weight coefficients of instantaneous rate of change, average rate of change, Sen slope and autoregressive coefficient, and the impact judgment value YPZ is used as the standard for measuring water quality changes.
[0021] Furthermore, the specific operation steps of the water quality monitoring module for analyzing the data detected by different sensors and predicting the time when the water quality reaches the standard are as follows:
[0022] First, determine the target water quality standards and requirements for sewage treatment, and obtain the real-time data of water quality parameters detected by the corresponding sensors through the multi-parameter sensor monitoring module, and clean and standardize the collected real-time data of water quality parameters;
[0023] Then use statistical methods or machine learning models to analyze the changing trends of water quality parameters, use historical data to train prediction models, and predict future changes in monitored water quality parameters. Use the trained models to predict the values of water quality parameters at specific points in the future.
[0024] According to the changing trend and model of current water quality parameters, the time required to reach the target water quality standard is estimated, and the predicted time is corrected in accordance with the correction rules; the correction rules collect the influencing parameters for comprehensive analysis to determine the degree of correction. The influencing parameters include:
[0025] The gap between the current water quality parameter value and the target value, the input load of pollutants, the treatment capacity score of the sewage treatment process and the change rate of the water quality parameters are normalized and the product of the gap between the current water quality parameter value and the target value and the input load of pollutants is used as the bottom circle radius, and the treatment capacity score of the sewage treatment process is used as the height to establish a cone model. The vertex of the cone model is selected as the sphere, and the change rate of the water quality parameter multiplied by the weight factor is used as the radius to establish a spherical model. The spherical model is cut on the cone model to form an irregular body. The volume of the irregular body is calculated and recorded as the shadow repair value. This shadow repair value is used to measure the influence of the influencing parameters on the degree of correction, where the weight factor is set between 1.5 and 2.2;
[0026] Then, the obtained image repair value is compared with the preset image repair threshold. When the image repair value is greater than the image repair threshold, correction is performed, and the difference between the image repair value and the preset image repair threshold is calculated, and the difference is compared with five preset image repair value difference intervals. The five image repair value difference intervals are respectively provided with different correction levels, and different correction levels are respectively provided with different estimated increase times. When it is determined that the image repair value difference interval to which the difference belongs is determined, the corresponding estimated increase time is obtained, and correction is performed based on the predicted required time according to the estimated increase time;
[0027] After completing the correction of the estimated time required to reach the target water quality standard, determine whether the time point reached is within the range of expected time points. When it is determined that the time point reached exceeds the expected time point, the optimization step is executed to intervene to ensure that the time when the real-time water quality reaches the target water quality standard is within the range of expected time points.
[0028] Furthermore, the specific operation steps of the multi-parameter sensor monitoring module for monitoring different parameters of water quality in the sewage treatment process through different sensors are as follows:
[0029] First, determine the water quality parameters that need to be monitored during sewage treatment, including pH, dissolved oxygen, chemical oxygen demand, ammonia nitrogen, total phosphorus, turbidity and temperature;
[0030] Then select the corresponding sensor according to the needs. Each sensor is targeted at specific water quality parameters, including: pH sensor, dissolved oxygen sensor, chemical oxygen demand sensor, ammonia nitrogen sensor, total phosphorus sensor, turbidity sensor, conductivity sensor, redox potential sensor, residual chlorine sensor, chlorophyll and blue-green algae sensor and oil in water sensor;
[0031] After determining the corresponding sensors, deploy them at key locations of sewage treatment, including water inlet, water outlet, corners and center;
[0032] After the deployment of sensors is completed, all deployed sensors are calibrated to ensure that all sensors can provide accurate measurement results, and test runs are performed to verify the overall performance and accuracy of the sensors;
[0033] After completing the test and determining that the overall performance and accuracy of the sensor meet the standards, the water quality parameter data collected by the sensor will be uploaded via wired or wireless means.
[0034] Furthermore, the specific operation steps of the optimization module to improve the water quality optimization speed of sewage treatment through the optimization steps are as follows:
[0035] First, conduct a comprehensive assessment of the current sewage treatment process, diagnose problem points, collect and analyze data, determine the key parameters that affect the progress of water quality optimization, and then adjust the sewage treatment process parameters based on the assessment results, including increasing aeration volume, adjusting pH value and increasing flocculant dosage, optimizing sludge return and discharge, and improving the effect of the activated sludge system;
[0036] Pre-set temporary treatment units, including adding mobile treatment equipment or activating backup treatment facilities, and adjust the process flow to strengthen pre-treatment measures and post-treatment measures. Pre-treatment measures include screening and sand settling to reduce the load of subsequent treatment units, and post-treatment measures include filtration and activated carbon adsorption to quickly improve the effluent quality;
[0037] Then use chemical flocculants and disinfectants to improve water quality parameters, introduce or increase microbial populations, and improve biological treatment efficiency; adjust the control strategy of the automated control system to achieve more precise process control, use real-time data to optimize the system, and improve response speed;
[0038] Record all adjustment measures and treatment effects, and report treatment progress regularly.
[0039] Furthermore, the specific operation steps of the visualization module to provide a visualization interface for real-time data display, historical data analysis, warning information and processing suggestions are as follows:
[0040] First, we conduct a survey of operators to obtain their specific monitoring needs, including data types, functional requirements, and operational convenience. Based on the results of the analysis, we design the layout of the interactive interface, functional modules, and user navigation process to ensure that the interactive design meets the user's actual workflow.
[0041] Design the integration of real-time and historical data from multi-parameter sensor monitoring modules, determine data interfaces and integration technologies, preset real-time data display modules, including dynamic charts and dashboards, and historical data analysis modules, including data query and comparative analysis tools;
[0042] Then preset warning rules, develop warning information display and notification mechanisms to ensure that operators can receive key warning information in a timely manner, integrate advanced data visualization components, and enhance the effect of data display;
[0043] The designed interactive module is then comprehensively tested, including functional testing, interface testing, performance testing, and security testing. The operating performance of the interactive module is monitored and optimized based on actual usage to ensure the stability and response speed of user interaction.
[0044] Compared with the prior art, the present invention has the following beneficial effects:
[0045] The present invention, through the adaptive data acquisition module, can dynamically adjust the data acquisition frequency according to the analysis results of the artificial intelligence algorithm to adapt to the real-time needs of water quality changes. This intelligent data acquisition method not only improves the monitoring efficiency, but also speeds up the response speed to water quality changes, making the sewage treatment process more flexible and accurate;
[0046] The present invention automatically adjusts the sewage treatment process parameters, such as increasing the aeration volume, adjusting the pH value, increasing the flocculant dosage, etc., according to the real-time monitoring data and historical data analysis results through the optimization module, which not only improves the efficiency of sewage treatment, but also helps to improve the effluent water quality and ensure that the target water quality standard is met;
[0047] The present invention provides an intuitive interface for real-time data display, historical data analysis, warning information and processing suggestions through a visualization module, which not only enables operators to grasp the water quality status in a timely and accurate manner, but also enhances the user interaction experience through integrated warning and decision support tools, assisting operators to make more scientific decisions. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;
[0049] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION
[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0051] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.
[0052] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.
[0053] like Figure 1 As shown, a water quality change monitoring system for sewage treatment includes:
[0054] Multi-parameter sensor monitoring module, used to monitor different parameters of water quality in the sewage treatment process through different sensors;
[0055] First, determine the water quality parameters that need to be monitored during sewage treatment, including pH, dissolved oxygen, chemical oxygen demand (COD), ammonia nitrogen, total phosphorus, turbidity and temperature; then select the corresponding sensor according to the needs. Each sensor targets specific water quality parameters, including:
[0056] pH sensor: monitors the pH value of water. pH value has an important influence on the metabolic activity of microorganisms in the sewage treatment process. Dissolved oxygen sensor: measures the concentration of dissolved oxygen in water, which is crucial to the metabolic activity of aerobic microorganisms. Chemical oxygen demand (COD) sensor: monitors the total amount of organic pollution in water, which is an important indicator for measuring the degree of organic pollution in water. Ammonia nitrogen sensor: measures the ammonia nitrogen content in water, which is one of the important indicators of eutrophication of water bodies. Total phosphorus sensor: monitors the phosphorus content in water, which is a key factor in eutrophication of water bodies. Turbidity sensor: measures the turbidity of water, reflecting the number of suspended particles in water. Conductivity sensor: monitors the conductivity of water, which can reflect the total amount of dissolved solids in water. Oxidation reduction potential (ORP) sensor: measures the redox potential of aqueous solution, and monitors the redox state in the sewage treatment process. Residual chlorine sensor: measures the amount of chlorine remaining after water treatment, which is used to evaluate the disinfection effect. Chlorophyll and blue-green algae sensors: monitor the presence of algae and warn of water blooms. Oil in water sensor: detects the content of oil in water, which is very important for industrial wastewater treatment.
[0057] After determining the corresponding sensors, deploy the sensors at key locations of sewage treatment, including the water inlet, outlet, corners and center. After completing the deployment of the sensors, calibrate all deployed sensors to ensure that all sensors can provide accurate measurement results, and perform test runs to verify the overall performance and accuracy of the sensors. After completing the test and determining that the overall performance and accuracy of the sensors meet the standards, upload the water quality parameter data collected by the sensors via wired or wireless means.
[0058] The adaptive data acquisition module is used to dynamically adjust the data acquisition frequency according to the analysis results of the artificial intelligence algorithm to adapt to the real-time needs of water quality changes;
[0059] In the initial stage, water quality parameter data is collected through the multi-parameter sensor monitoring module at a preset fixed frequency, and then the collected raw data is cleaned, including noise removal, missing value filling and data standardization; useful features are extracted from the raw data, including the changing trend, seasonal pattern and periodic change of water quality parameters, and a data model is established using a machine learning algorithm to predict the changing trend and potential abnormal conditions of water quality parameters; the real-time collected data is input into the data model for immediate analysis to obtain a prediction of the current water quality status, and an adaptive algorithm is used to dynamically adjust the data collection frequency according to the prediction results of the data model and the preset logical rules. Specifically, the water quality change speed is comprehensively evaluated through the measurement parameters obtained. When the water quality changes slowly, the data collection frequency is reduced to save resources; when the water quality changes drastically or approaches the preset threshold, the data collection frequency is increased to obtain more accurate monitoring; the measurement parameters include:
[0060] Instantaneous rate of change: A high instantaneous rate of change means that the water quality parameters change rapidly in a short period of time, indicating that the water quality changes rapidly; Average rate of change: If the change in water quality parameters is large over a long period of time, it indicates that the water quality changes rapidly; Sen slope: As a robust estimate of the trend slope, a larger absolute value of the Sen slope indicates that the water quality changes rapidly; Time series analysis parameters (such as parameters of the ARIMA model): The autoregressive coefficient in the time series model, the absolute value of the autoregressive coefficient is obtained. The larger the absolute value of the autoregressive coefficient, the stronger the impact of the current value on the future value. Whether it is positive or negative correlation, a larger absolute value may mean that the water quality parameter changes rapidly;
[0061] Then the instantaneous rate of change, average rate of change, Sen slope and absolute value of autoregressive coefficient are calibrated as ss, pb, sn and hg respectively, and after normalization, they are entered into the following formula: To get the shadow judgment value YPZ, where They are preset weight coefficients of instantaneous rate of change, average rate of change, Sen slope and autoregressive coefficient, and are set to 1-1.23, 0.93-0.96, 0.85-0.89 and 0.65-0.69 respectively; and this shadow judgment value YPZ is used as a standard for measuring water quality changes; the obtained shadow judgment value YPZ is compared with several preset shadow judgment value intervals, and different monitoring and adjustment frequencies are set for the several shadow judgment value intervals respectively. When the shadow judgment value interval to which the shadow judgment value YPZ belongs is determined, the monitoring data is acquired at the corresponding monitoring and adjustment frequency at the current moment.
[0062] The water quality monitoring module is used to analyze the data detected by different sensors and predict the time when the water quality reaches the standard;
[0063] First, determine the target water quality standards and requirements for sewage treatment, and obtain the real-time data of water quality parameters detected by the corresponding sensors through the multi-parameter sensor monitoring module, and clean and standardize the collected real-time data of water quality parameters for analysis; then use statistical methods or machine learning models to analyze the changing trends of water quality parameters, use historical data to train prediction models, and predict future changes in monitored water quality parameters, and use the trained models to predict the values of water quality parameters at specific points in the future; then estimate the time required to reach the target water quality standard based on the current changing trends and models of water quality parameters, and use correction rules to correct the predicted time; the correction rules determine the degree of correction by collecting influencing parameters for comprehensive analysis, and the influencing parameters include:
[0064] The gap between the current water quality parameter value and the target value, the input load of pollutants, the treatment capacity score of the sewage treatment process and the change rate of water quality parameters are normalized and the product of the gap between the current water quality parameter value and the target value and the input load of pollutants is used as the bottom circle radius, and the treatment capacity score of the sewage treatment process is used as the height to establish a cone model. The vertex of the cone model is selected as the sphere, and the change rate of the water quality parameter multiplied by the weight factor is used as the radius to establish a spherical model. The spherical model is cut on the cone model to form an irregular body. The volume of the irregular body is calculated and recorded as the shadow repair value. This shadow repair value is used to measure the influence of the influencing parameters on the degree of correction, where the weight factor is set between 1.5 and 2.2; the obtained shadow repair value is then compared with the preset shadow repair threshold. When the image correction value is greater than the image correction threshold, correction is made, and the difference between the image correction value and the preset image correction threshold is calculated, and the difference is compared with the preset five image correction value difference intervals. The five image correction value difference intervals are respectively provided with different correction levels, and different correction levels are respectively provided with different estimated increase times. When it is determined that the image correction value difference interval to which the difference belongs, the corresponding estimated increase time is obtained, and correction is made on the basis of the predicted required time according to the estimated increase time; after completing the correction of the estimated time required to reach the target water quality standard, determine whether the time point reached is within the range of the expected time point. When it is determined that the time point reached exceeds the expected time point, the optimization step is executed to interfere, so as to ensure that the time when the real-time water quality reaches the target water quality standard is within the range of the expected time point.
[0065] The optimization module is used to improve the water quality optimization speed of sewage treatment through optimization steps; the specific process of the optimization steps is as follows:
[0066] First, conduct a comprehensive assessment of the current sewage treatment process, diagnose problem points, collect and analyze data, determine the key parameters that affect the progress of water quality optimization, and then adjust the sewage treatment process parameters based on the assessment results, including increasing the aeration volume, adjusting the pH value, increasing the amount of flocculants added, etc., to optimize sludge return and discharge, and improve the effect of the activated sludge system; preset temporary treatment units, including adding mobile treatment equipment or starting backup treatment facilities, and adjust the process flow, such as pre-treatment by diverting part of the sewage, strengthening pre-treatment measures and post-treatment measures. Pre-treatment measures include screening and sand settling to reduce the load of subsequent treatment units, and post-treatment measures include filtration and activated carbon adsorption to quickly improve the effluent quality; then use chemical flocculants, disinfectants, etc. to quickly improve water quality parameters, introduce or increase microbial populations, and improve biological treatment efficiency; adjust the control strategy of the automated control system to achieve more precise process control, use real-time data to optimize the system, and improve response speed; record all adjustment measures and treatment effects, and report treatment progress regularly.
[0067] The visualization module is used to provide a visualization interface for real-time data display, historical data analysis, warning information and processing suggestions, which is convenient for operators to monitor and manage;
[0068] First, we conducted a survey of operators to obtain the specific monitoring needs of operators of sewage treatment, including data types, functional requirements and operational convenience. Based on the results of the analysis, we designed the layout of the interactive interface, functional modules and user navigation process to ensure that the interactive design meets the actual workflow of users. We designed the integration of real-time data and historical data from the multi-parameter sensor monitoring module, determined the data interface and integration technology, and preset the real-time data display module, including dynamic charts and dashboards, and the historical data analysis module, including data query and comparative analysis tools.
[0069] Then preset warning rules, develop warning information display and notification mechanisms to ensure that operators can receive key warning information in a timely manner, integrate advanced data visualization components, enhance data display effects, and improve user experience; then conduct comprehensive testing on the designed interactive modules, including functional testing, interface testing, performance testing, and security testing, monitor the operating performance of the interactive modules, and optimize them according to actual usage to ensure the stability and response speed of user interaction.
[0070] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A water quality change monitoring system for sewage treatment, characterized in that: include: Multi-parameter sensor monitoring module, used to monitor different parameters of water quality in the sewage treatment process through different sensors; Adaptive data collection module: According to the analysis results of the artificial intelligence algorithm, the data collection frequency is dynamically adjusted to meet the real-time needs of water quality changes. The specific steps are as follows: In the initial stage, water quality parameter data is collected through the multi-parameter sensor monitoring module at a preset fixed frequency, and then the collected raw data is cleaned, including noise removal, missing value filling and data standardization; Extract useful features from raw data, including trends, seasonal patterns, and periodic changes in water quality parameters, and use machine learning algorithms to build data models to predict trends and potential anomalies in water quality parameters; The real-time collected data is input into the data model for immediate analysis to obtain the current water quality status prediction. The adaptive algorithm is used to dynamically adjust the data collection frequency according to the prediction results of the data model and the preset logical rules. Specifically, the influence judgment value is obtained by comprehensively evaluating and analyzing the water quality change speed through the obtained measurement parameters, and this influence judgment value is used as the standard for measuring water quality changes. The influence judgment value analysis process is as follows: The measurement parameters include: instantaneous rate of change of water quality, average rate of change, Sen slope and time series analysis parameters, wherein the time series analysis parameters are obtained by obtaining the autoregressive coefficient in the time series model to obtain the absolute value of the autoregressive coefficient. The larger the absolute value of the autoregressive coefficient, the stronger the influence of the current value on the future value. Then the instantaneous rate of change, average rate of change, Sen slope and absolute value of autoregressive coefficient are calibrated as ss, pb, sn and hg respectively, and after normalization, they are entered into the following formula: To get the shadow judgment value YPZ, where They are the preset weight coefficients of instantaneous rate of change, average rate of change, Sen slope and autoregressive coefficient, and the impact judgment value YPZ is used as the standard for measuring water quality changes; The obtained shadow judgment value is compared with several preset shadow judgment value intervals, and different monitoring and adjustment frequencies are set corresponding to the several shadow judgment value intervals. When the shadow judgment value interval to which the shadow judgment value belongs is determined, the monitoring data is obtained at the current moment according to the corresponding monitoring and adjustment frequency; The water quality monitoring module is used to analyze the data detected by different sensors and predict the time when the water quality reaches the standard. The specific operation steps are as follows: First, determine the target water quality standards and requirements for sewage treatment, and obtain the real-time data of water quality parameters detected by the corresponding sensors through the multi-parameter sensor monitoring module, and clean and standardize the collected real-time data of water quality parameters; Then use statistical methods or machine learning models to analyze the changing trends of water quality parameters, use historical data to train prediction models, and predict future changes in monitored water quality parameters. Use the trained models to predict the values of water quality parameters at specific points in the future. According to the changing trend and model of current water quality parameters, the time required to reach the target water quality standard is estimated, and the predicted time is corrected in accordance with the correction rules; the correction rules collect the influencing parameters for comprehensive analysis to determine the degree of correction. The influencing parameters include: The gap between the current water quality parameter value and the target value, the input load of pollutants, the treatment capacity score of the sewage treatment process and the change rate of the water quality parameters are normalized and the product of the gap between the current water quality parameter value and the target value and the input load of pollutants is used as the bottom circle radius, and the treatment capacity score of the sewage treatment process is used as the height to establish a cone model. The vertex of the cone model is selected as the sphere, and the change rate of the water quality parameter multiplied by the weight factor is used as the radius to establish a spherical model. The spherical model is cut on the cone model to form an irregular body. The volume of the irregular body is calculated and recorded as the shadow repair value. This shadow repair value is used to measure the influence of the influencing parameters on the degree of correction, where the weight factor is set between 1.5 and 2.2; Then, the obtained image repair value is compared with the preset image repair threshold. When the image repair value is greater than the image repair threshold, correction is performed, and the difference between the image repair value and the preset image repair threshold is calculated, and the difference is compared with five preset image repair value difference intervals. The five image repair value difference intervals are respectively provided with different correction levels, and different correction levels are respectively provided with different estimated increase times. When it is determined that the image repair value difference interval to which the difference belongs is determined, the corresponding estimated increase time is obtained, and correction is performed based on the predicted required time according to the estimated increase time; After completing the correction of the estimated time required to reach the target water quality standard, it is determined whether the time point reached is within the range of the expected time point. When it is determined that the time point reached exceeds the expected time point, the optimization step is executed to intervene to ensure that the time when the real-time water quality reaches the target water quality standard is within the range of the expected time point; The optimization module is used to improve the water quality optimization speed of sewage treatment through optimization steps. The specific operation steps are as follows: First, conduct a comprehensive assessment of the current sewage treatment process, diagnose problem points, collect and analyze data, determine the key parameters that affect the progress of water quality optimization, and then adjust the sewage treatment process parameters based on the assessment results, including increasing aeration volume, adjusting pH value and increasing flocculant dosage, optimizing sludge return and discharge, and improving the effect of the activated sludge system; Pre-set temporary treatment units, including adding mobile treatment equipment or activating backup treatment facilities, and adjust the process flow to strengthen pre-treatment measures and post-treatment measures. Pre-treatment measures include screening and sand settling to reduce the load of subsequent treatment units, and post-treatment measures include filtration and activated carbon adsorption to quickly improve the effluent quality; Then use chemical flocculants and disinfectants to improve water quality parameters, introduce or increase microbial populations, and improve biological treatment efficiency; adjust the control strategy of the automated control system to achieve more precise process control, use real-time data to optimize the system, and improve response speed; Record all adjustment measures and treatment effects, and report treatment progress regularly; The visualization module is used to provide a visual interface for real-time data display, historical data analysis, warning information and processing suggestions, which is convenient for operators to monitor and manage.
2. A water quality change monitoring system for sewage treatment according to claim 1, characterized in that: The specific operation steps of the multi-parameter sensor monitoring module for monitoring different parameters of water quality in the sewage treatment process through different sensors are as follows: First, determine the water quality parameters that need to be monitored during sewage treatment, including pH, dissolved oxygen, chemical oxygen demand, ammonia nitrogen, total phosphorus, turbidity and temperature; Then select the corresponding sensor according to the needs. Each sensor is targeted at specific water quality parameters, including: pH sensor, dissolved oxygen sensor, chemical oxygen demand sensor, ammonia nitrogen sensor, total phosphorus sensor, turbidity sensor, conductivity sensor, redox potential sensor, residual chlorine sensor, chlorophyll and blue-green algae sensor and oil in water sensor; After determining the corresponding sensors, deploy them at key locations of sewage treatment, including water inlet, water outlet, corners and center; After the deployment of sensors is completed, all deployed sensors are calibrated to ensure that all sensors can provide accurate measurement results, and test runs are performed to verify the overall performance and accuracy of the sensors; After completing the test and determining that the overall performance and accuracy of the sensor meet the standards, the water quality parameter data collected by the sensor will be uploaded via wired or wireless means.
3. A water quality change monitoring system for sewage treatment according to claim 1, characterized in that: The specific operation steps of the visualization module to provide a visualization interface for real-time data display, historical data analysis, warning information and processing suggestions are as follows: First, we conduct a survey of operators to obtain their specific monitoring needs, including data types, functional requirements, and operational convenience. Based on the results of the analysis, we design the layout of the interactive interface, functional modules, and user navigation process to ensure that the interactive design meets the user's actual workflow. Design the integration of real-time and historical data from multi-parameter sensor monitoring modules, determine data interfaces and integration technologies, preset real-time data display modules, including dynamic charts and dashboards, and historical data analysis modules, including data query and comparative analysis tools; Then preset warning rules, develop warning information display and notification mechanisms to ensure that operators can receive key warning information in a timely manner, integrate advanced data visualization components, and enhance the effect of data display; The designed interactive module is then comprehensively tested, including functional testing, interface testing, performance testing, and security testing. The operating performance of the interactive module is monitored and optimized based on actual usage to ensure the stability and response speed of user interaction.
Citation Information
Cited By
Water pollution composite treatment method and system based on water quality pollution real-time monitoring
CN120181299A
Sewage quality online monitoring method and system
CN121765292A
A sewage water quality on-line monitoring method and system
CN121765292B
