Online Monitoring Method, System, Equipment and Medium for Industrial Wastewater Treatment

Abstract

The present invention discloses an online monitoring method, system, device and medium for industrial wastewater treatment, including determining key sampling areas for monitoring at each treatment stage of industrial wastewater, and sequentially connecting them in the order of treatment stages to generate candidate monitoring paths; performing correlation analysis on the reference monitoring path and the candidate monitoring paths to determine the target monitoring path for this time; constructing an optimization model, using 0-1 integer programming to solve to determine the positions and quantities of target sampling points in each key sampling area, and combining the sampling period to determine the first monitoring plan; predicting the water quality change trend in each key sampling area based on historical monitoring data and the current monitoring results, constructing a correction model according to the water quality change trend, dynamically adjusting the first monitoring plan and using it for the monitoring of the next cycle. The present invention can flexibly plan the monitoring path, scientifically select the positions and quantities of monitoring points, dynamically adjust the monitoring plan in combination with historical data, improve the monitoring efficiency and quality, and reduce the monitoring cost.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial wastewater treatment, and particularly to an online monitoring method, system, device and medium for industrial wastewater treatment. Background Art

[0002] The treatment and discharge of industrial wastewater is one of the important links in the environmental protection field. In order to ensure the effective treatment of industrial wastewater and meet the national or local discharge standards, it is crucial to monitor the water quality parameters at each stage of the treatment process in real time.

[0003] However, traditional online monitoring methods for industrial wastewater usually have the following deficiencies: 1) Monitoring points are usually set based on experience or fixed patterns, lacking scientific basis, and cannot accurately reflect the key change points in the wastewater treatment process, resulting in insufficient representativeness of monitoring data and inability to detect abnormal situations in the treatment process in a timely manner. Both the number and location of monitoring points are set unreasonably. 2) In actual applications, due to the complex and variable layout of treatment facilities, traditional methods are difficult to quickly adapt to changes in different treatment stages, resulting in low monitoring efficiency and high costs; 3) The monitoring path planning is not flexible. Once the monitoring plan is formulated, it cannot be adjusted in a timely manner according to the actual situation, and it is difficult to quickly respond to problems of abnormal water quality treatment, thus possibly missing the best treatment opportunity and affecting the overall monitoring quality and energy efficiency. Summary of the Invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present invention provides an online monitoring method, system, device and medium for industrial wastewater treatment.

[0005] In a first aspect, the present invention provides an online monitoring method for industrial wastewater treatment, and the method includes:

[0006] Determine the key sampling areas for monitoring at each treatment stage of industrial wastewater according to historical monitoring data, and connect different key sampling areas in sequence according to the order of treatment stages to generate several candidate monitoring paths;

[0007] Determine a reference monitoring path based on historical monitoring cases in the database, perform a correlation analysis on the reference monitoring path and several candidate monitoring paths, and use the candidate monitoring path with the maximum correlation as the target monitoring path for this monitoring;

[0008] Construct an optimization model for sampling points, use 0-1 integer programming to solve the model, determine the number and location of target sampling points in each key sampling area of the target monitoring path according to the solution result, and determine the first monitoring plan according to the sampling period and the number and location of target sampling points;

[0009] Execute the first monitoring plan to obtain the current monitoring results, predict the water quality change trend of each key sampling area based on historical monitoring data and the current monitoring results, construct a correction model according to the water quality change trend, and use the correction model to dynamically adjust the first monitoring plan and apply it to the monitoring process of the next cycle.

[0010] Preferably, the optimization model for constructing sampling points is solved using 0-1 integer programming and includes:

[0011] Construct the objective function of the optimization model:

[0012] ;

[0013] Determine the constraint conditions:

[0014] ;

[0015] , ;

[0016] ; ;

[0017] In the formula, is the objective function, represents the th key sampling area, and there are a total of ; represents the th sampling point, and there are a total of ; represents the importance weight of the th key sampling area, represents the distance from the th key sampling area to the th sampling point, represents whether the th sampling point is selected, 1 means selected, 0 means not selected; is the upper limit of the number of sampling points, represents the upper limit of the distance of a single , represents the upper limit of the distance of all ;

[0018] Solve the objective function using 0-1 integer programming to determine the number and location of the target sampling points in each key sampling area.

[0019] Preferably, constructing the correction model according to the water quality change trend includes:

[0020] In the first monitoring plan, let the number of initial target sampling points in the th key sampling area be , the position set is , satisfies , indicating the initial position of the th target sampling point in the th key sampling area;

[0021] Based on the water quality change trend, the water quality change rate of the th key sampling area within the time is , then it satisfies:

[0022] ;

[0023] ;

[0024] In the formula, represents the updated number of target sampling points, represents the importance weight of the th key sampling area; represents the position of the updated target sampling point, is a random vector, representing the offset direction of the target sampling point position; is the natural constant, , are adjustment factors, which are used to adjust the change ranges of the number and position of the target sampling points respectively, and satisfy .

[0025] In the second aspect, the present invention also provides an on-line monitoring system for industrial wastewater treatment, and the system includes:

[0026] A candidate path determination unit, configured to determine key sampling areas monitored in each treatment stage of industrial wastewater according to historical monitoring data, connect different key sampling areas in sequence according to the order of treatment stages, and generate several candidate monitoring paths;

[0027] A target path determination unit, configured to determine a reference monitoring path based on historical monitoring cases in a database, perform a correlation analysis on the reference monitoring path and several candidate monitoring paths, and use the candidate monitoring path with the maximum correlation as the target monitoring path for this monitoring;

[0028] A monitoring plan generation unit, configured to construct an optimization model of sampling points, solve the model using 0-1 integer programming, determine the number and position of target sampling points in each key sampling area of the target monitoring path according to the solution result, and determine the first monitoring plan according to the sampling period and the number and position of target sampling points;

[0029] The monitoring plan adjustment unit is used to execute the first monitoring plan to obtain the current monitoring results, predict the water quality change trend of each key sampling area based on the historical monitoring data and the current monitoring results, construct a correction model according to the water quality change trend, and use the correction model to dynamically adjust the first monitoring plan and apply it to the monitoring process of the next cycle.

[0030] Preferably, the monitoring plan generation unit is further used for:

[0031] Construct the objective function of the optimization model:

[0032] ;

[0033] Determine the constraint conditions:

[0034] ;

[0035] , ;

[0036] ; ;

[0037] In the formula, is the objective function, represents the th key sampling area, and there are in total; represents the th sampling point, and there are in total; represents the importance weight of the th key sampling area, represents the distance from the th key sampling area to the th sampling point, represents whether the th sampling point is selected, 1 means selected, 0 means not selected; is the upper limit of the number of sampling points, represents the upper limit of the distance of a single , represents the upper limit of the distance of all ;

[0038] Use 0-1 integer programming to solve the objective function and determine the number and location of the target sampling points in each key sampling area.

[0039] Preferably, the monitoring plan adjustment unit is further used for:

[0040] Assume that in the first monitoring plan, the initial number of target sampling points in the th key sampling area is , the position set is , Satisfy , Indicates the th initial position of the th target sampling point in the key sampling area;

[0041] Based on the water quality change trend, the water quality change rate of the th key sampling area within the time is , then the adjusted number and position of the target sampling points satisfy the following relationship:

[0042] ;

[0043] ;

[0044] In the formula, represents the updated number of target sampling points, represents the th importance weight of the key sampling area; represents the position of the updated target sampling point, is a random vector, representing the offset direction of the target sampling point position; is the natural constant, , are adjustment factors, respectively used to adjust the change ranges of the number and position of the target sampling points, satisfying .

[0045] In the third aspect, the present invention further provides an electronic device, including a processor and a memory. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the method according to the first aspect and any one of its possible implementation manners as described above.

[0046] In the fourth aspect, the present invention further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor of the electronic device, the processor is caused to execute the method according to the first aspect and any one of its possible implementation manners as described above.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0048] 1) By analyzing historical monitoring data, key sampling areas at each treatment stage are determined, and statistical methods such as correlation analysis are used to select the optimal path from numerous candidate monitoring paths. This not only improves the accuracy of monitoring point selection but also ensures that the monitoring data is more comprehensive and representative. Based on historical cases in the database, different monitoring paths are dynamically generated and evaluated, and the best path that most conforms to the current treatment conditions is selected, thereby effectively coping with changes in the treatment process and improving the flexibility and adaptability of the monitoring work.

[0049] 2) By constructing an optimization model for sampling points, using a 0-1 integer programming solution model, according to the solution results, the number and location of target sampling points in each key sampling area of the target monitoring path are determined. According to the sampling period and the number and location of target sampling points, the first monitoring plan is determined. Through the optimization solution of the optimization model, scientific sampling point positions and numbers can be obtained first, making the first monitoring plan more reasonable.

[0050] 3) Combining historical monitoring data with real-time monitoring results, a water quality change trend prediction model is established to provide a basis for the optimization of subsequent monitoring plans. In this way, potential problems can be predicted in advance to respond in a timely manner to abnormal water quality treatment situations. In addition, the present invention also introduces a correction model to dynamically adjust the monitoring plan according to the water quality change trend, so as to dynamically change the number and location of target sampling points and ensure that the monitoring strategy is always in the best state. Through this dynamic adjustment mechanism, the monitoring efficiency can be improved and the operation cost can be reduced, while ensuring the accuracy and reliability of the monitoring results.

[0051] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the drawings required to be used in the embodiments of the present invention or the background art will be described below.

[0053] The drawings here are incorporated into the specification and form a part of this specification. These drawings show embodiments that conform to the present disclosure and are used together with the specification to explain the technical solutions of the present disclosure.

[0054] Figure 1 It is a schematic flow chart of an online monitoring method for industrial wastewater treatment provided by an embodiment of the present invention;

[0055] Figure 2 It is a schematic structural diagram of an online monitoring system for industrial wastewater treatment provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with 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 of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] Reference to "embodiment" in this context means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0058] In the current monitoring process of industrial wastewater treatment, the selection of sampling points for monitoring is often based on manual experience or fixed patterns, unable to reasonably control the location and quantity of sampling points, thus increasing the monitoring time and cost, and unable to ensure the accuracy and reliability of monitoring results. For this reason, the present invention aims to provide an online monitoring method for industrial wastewater treatment, which can scientifically select monitoring paths for the wastewater treatment stage to ensure that no monitoring link is missed, and then optimize and solve the sampling point optimization model based on the monitoring paths to scientifically guide the location and quantity of sampling points in the first solution; finally, combine historical data and prediction models to predict the water quality change trends in each sampling area, and introduce a correction model to dynamically adjust the selection of sampling points in the monitoring plan, thereby greatly improving the monitoring efficiency and the accuracy of monitoring results, while reducing the monitoring cost.

[0059] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of an online monitoring method for industrial wastewater treatment provided by an embodiment of the present invention. As Figure 1 shown, the method includes:

[0060] S10. Determine the key sampling areas for monitoring in each treatment stage of industrial wastewater according to historical monitoring data, and connect different key sampling areas in sequence according to the order of treatment stages to generate several candidate monitoring paths.

[0061] To help understanding, first, each treatment stage of industrial wastewater will be described:

[0062] Entrance: The first point where wastewater enters the treatment facility, used to understand the basic characteristics of untreated wastewater, such as pH value, temperature, suspended solids (SS), chemical oxygen demand (COD), biochemical oxygen demand (BOD), etc.;

[0063] Pretreatment stage: The grille checks the removal of large particles, the grit chamber evaluates the removal efficiency of inorganic particles, and the equalization basin monitors the stability of water quality and quantity;

[0064] Primary treatment stage: Detect the preliminary removal effect of suspended substances and the change in the content of organic matter;

[0065] Biological treatment stage: The aeration tank monitors the dissolved oxygen level, microbial activity, ammonia nitrogen conversion rate, etc. to evaluate the effect of the biodegradation process; The secondary sedimentation tank further confirms the improvement of water quality after biological treatment;

[0066] Advanced treatment stage: The coagulation / flocculation reactor observes the coagulation effect of colloids and fine particles; The filter detects the ability to filter out tiny suspended particles; The activated carbon adsorption tower evaluates the adsorption effect on specific pollutants (such as organic matter, heavy metals);

[0067] Disinfection treatment stage: The disinfection tank ensures that pathogens are effectively killed to meet the requirements of the microbial indicators in the discharge standard;

[0068] Final discharge outlet: The last treatment stage, used to verify the effectiveness of the entire treatment process and ensure that the effluent meets the national or local discharge standards.

[0069] In this step, first, it is necessary to collect the industrial wastewater treatment data over a past period, such as the past year. These data should include but are not limited to key water quality indicators such as pH value, chemical oxygen demand (COD), biochemical oxygen demand (BOD), total suspended solids (TSS), etc., and the changes of these indicators in different treatment stages. Conduct an in-depth analysis of the collected data to identify which treatment stages or areas have large fluctuations in water quality parameters, or which areas often exceed the standards. Usually, these areas are regarded as key sampling areas. For example, if high-concentration suspended solids are frequently detected in the water sample after the primary sedimentation tank, this area can be regarded as a key sampling area. It can be understood that each treatment stage can contain at least one key sampling area, or no key sampling area may be marked because the treatment results are relatively stable, and only routine monitoring is required.

[0070] Preferably, when determining the key sampling areas, cluster analysis can be used for rapid screening. For example, according to the historical sampling data, determine the starting and ending points of sampling for each treatment stage, and conduct clustering separately to form multiple clusters; then merge the clusters whose center distances are less than the distance threshold to obtain multiple target clusters; finally, analyze which target cluster contains the largest number of starting and ending points, and it can be marked as the key sampling area.

[0071] Once the key sampling areas for all treatment stages are determined, these key sampling areas can be connected in the sequence of the wastewater treatment process to form one or more possible monitoring paths. Each path represents a possible monitoring plan, that is, how to select sampling points for monitoring throughout the entire process from the entry of wastewater into the treatment facility, through a series of treatment units, until the final discharge or reuse.

[0072] S20. Determine the reference monitoring path based on historical monitoring cases in the database, conduct a correlation analysis on the reference monitoring path and several candidate monitoring paths, and use the candidate monitoring path with the highest correlation as the target monitoring path for this monitoring.

[0073] In this step, first, based on the above-mentioned historical monitoring data, perform data cleaning to remove invalid or incorrect data to ensure the accuracy and integrity of the data. Then, classify the historical monitoring cases according to different wastewater types, treatment processes, and treatment scales to obtain multiple different types of monitoring cases. Then, extract key features from each historical monitoring case, such as the location of sampling points, the change trend of monitoring indicators, the sequence of treatment stages, etc. According to the extracted features, construct the reference monitoring path for each type. The reference monitoring path should be able to reflect the typical monitoring requirements during the wastewater treatment process of this type.

[0074] Furthermore, conduct a correlation analysis for path matching, including matching the generated several candidate monitoring paths with each reference monitoring path and calculating the similarity or correlation between them. When analyzing the correlation, correlation analysis methods such as Pearson correlation coefficient and cosine similarity can be used to quantify the similarity degree between the candidate monitoring path and the reference monitoring path. Finally, select the candidate monitoring path with the highest correlation as the target monitoring path for this monitoring. If the correlations of multiple paths are the same or close, the path with the lowest cost or the highest efficiency can be selected.

[0075] Therefore, the above-mentioned implementation method first determines the key sampling areas, generates candidate monitoring paths, and then determines the target monitoring path through path matching, and determines the reference monitoring path through historical monitoring cases, ensuring that the selected monitoring path has a scientific basis and can better reflect the key change points during the wastewater treatment process. Based on the analysis of historical data and correlation calculation, the error caused by human factors can be reduced, and the reliability of the monitoring results can be improved. By selecting the candidate monitoring path with the highest correlation, the distribution of sampling points and the sampling frequency can be optimized on the premise of ensuring the monitoring effect, and the monitoring cost can be reduced. At the same time, the monitoring path can be dynamically adjusted to avoid ineffective or repeated monitoring and improve the overall efficiency of the monitoring work.

[0076] S30. Construct an optimization model for sampling points, solve the model using 0-1 integer programming, determine the number and location of target sampling points in each key sampling area on the target monitoring path according to the solution results, and determine the first monitoring plan according to the sampling period and the number and location of target sampling points.

[0077] Specifically, the construction of the optimization model for sampling points and the solution of the model using 0-1 integer programming include:

[0078] Construct the objective function of the optimization model:

[0079] ;

[0080] Determine the constraint conditions:

[0081] ;

[0082] , ;

[0083] ; ;

[0084] In the formula, is the objective function, represents the th key sampling area, with a total of ; represents the th sampling point, with a total of ; represents the importance weight of the th key sampling area, represents the distance from the th key sampling area to the th sampling point, represents whether the th sampling point is selected, 1 means selected, 0 means not selected; is the upper limit of the number of sampling points, represents the upper limit of the distance of a single , represents the upper limit of the distance of all ;

[0085] Solve the objective function using 0-1 integer programming to determine the number and location of target sampling points in each key sampling area.

[0086] In the above process, the variables are , while is the known importance weight, is the known sampling point distance characterization. That is, it is necessary to determine , after determining which sampling points are selected, the number of target sampling points can be counted, and the position of the target sampling points can be determined by matching the known When determining the position of the target sampling points, only the objective function and constraints need to be input into the linear programming software, and the optimal solution can be quickly obtained by running the solver. After determining the number and position of the target sampling points, the sampling period also needs to be determined. Initially, historical monitoring data can be referred to, the water quality change trends under different sampling periods can be analyzed, and a period that can effectively capture water quality changes can be selected. At the same time, the monitoring cost and monitoring effect can be balanced, and a sampling period that can take both cost and quality into account can be selected. For example, it is determined that the next monitoring time is one month after this monitoring.

[0087] In this embodiment, by constructing an optimization model, it is ensured that the selection of sampling points has a scientific basis and can better reflect the key change points in the wastewater treatment process. Based on mathematical models and optimization algorithms, the errors caused by human factors are reduced, and the accuracy of monitoring results is improved. Through the 0-1 integer programming solution model, the distribution of sampling points and the sampling frequency can be optimized on the premise of ensuring the monitoring effect, and the monitoring cost can be reduced.

[0088] S40. Execute the first monitoring plan to obtain the monitoring results of this time. Predict the water quality change trends of each key sampling area based on the historical monitoring data and the monitoring results of this time. Construct a correction model according to the water quality change trends, and use the correction model to dynamically adjust the first monitoring plan and apply it to the monitoring process of the next cycle.

[0089] Specifically, predicting the water quality change trends includes the following steps:

[0090] 1) Data preprocessing: Preprocess the historical monitoring data and the monitoring results of this time, including data cleaning, missing value processing, and outlier detection. Standardize or normalize the data for subsequent analysis and modeling.

[0091] 2) Trend analysis: Use time series analysis methods, such as the ARIMA model, exponential smoothing method, etc., to analyze the historical data and the monitoring results of this time for each key sampling area, and identify the change trends of water quality indicators. Further, visually display the water quality change trends, such as drawing time series graphs, trend graphs, etc., to help intuitively understand the water quality change rules.

[0092] 3) Prediction model construction: Based on the trend analysis results, select a suitable prediction model, such as linear regression, neural network, random forest, etc., to predict the water quality change trends. Preferably, the LSTM model is used for prediction.

[0093] Preferably, the training of the prediction model can be carried out in the following manner: using the preprocessed data as the training set, extracting features from the training samples, performing feature dimensionality reduction on the extracted features using the PCA algorithm, fitting the dimensionality-reduced features according to the gradient boosting tree algorithm, and screening out the feature quantity with the largest correlation from the fitted features; fusing the water quality change rate with the feature quantity with the largest correlation to train the LSTM model network model with a self-attention mechanism; constructing a loss function using the root mean square error. If the value of the loss function is greater than the preset value, screening out the feature quantity with the secondary correlation from the fitted features to reconstruct the fused features and iteratively train the LSTM model network model until the value of the loss function is less than the preset value, then generating the prediction model.

[0094] In one embodiment, constructing the correction model according to the water quality change trend includes:

[0095] In the first monitoring plan, let the number of initial target sampling points in the th key sampling area be , and the position set be , satisfying , denoting the initial position of the th target sampling point in the th key sampling area;

[0096] Based on the water quality change trend, the water quality change rate within time in the th key sampling area is obtained as , then satisfying:

[0097] ;

[0098] ;

[0099] In the formula, denotes the updated number of target sampling points, denotes the importance weight of the th key sampling area; denotes the position of the updated target sampling point, is a random vector, representing the offset direction of the target sampling point position; is the natural constant, , are adjustment factors, respectively used to adjust the change range of the number and position of target sampling points, satisfying .

[0100] For the sake of understanding, specific numerical values will be substituted for illustration below:

[0101] Assume that the industrial wastewater treatment process includes 3 key sampling areas, and the initial monitoring plan is as follows:

[0102] Key sampling area 1: Initial target number of sampling points , location set ;

[0103] Key sampling area 2: Initial target number of sampling points , location set ;

[0104] Key sampling area 3: Initial target number of sampling points , location set ;

[0105] The importance weights of each key sampling area are respectively: , , ;

[0106] Based on historical data and the results of this monitoring, the water quality change rates of each key sampling area within time are:

[0107] , , , adjustment factor ;

[0108] ; ; ;

[0109] After substitution and calculation, , , ;

[0110] ; ; ;

[0111] Among them, the coordinate unit of the location is .

[0112] Therefore, by dynamically adjusting the number of sampling points, unnecessary sampling points can be reduced and the monitoring cost can be lowered on the premise of ensuring the monitoring effect. Dynamically adjusting the sampling point locations can avoid ineffective or repeated monitoring and improve the overall efficiency of the monitoring work. Combining with the prediction of the water quality change trend can greatly improve the accuracy and reliability of the sampling point adjustment and enhance the monitoring energy efficiency.

[0113] Finally, multiply the total duration of this cycle by the cycle correction coefficient The interval until the next monitoring period can be determined. In this embodiment, the monitoring period is dynamically adjusted according to the water quality change trend and monitoring results, ensuring that the monitoring plan can better reflect the water quality change and improving the accuracy and reliability of monitoring.

[0114] In summary, the method provided by the present invention achieves at least the following beneficial effects:

[0115] 1) By analyzing historical monitoring data, key sampling areas at each treatment stage are determined, and statistical methods such as correlation analysis are used to select the optimal path from numerous candidate monitoring paths. This not only improves the accuracy of monitoring point selection but also ensures that the monitoring data is more comprehensive and representative. Based on historical cases in the database, different monitoring paths are dynamically generated and evaluated, and the best path that most conforms to the current treatment conditions is selected, thus effectively coping with changes in the treatment process and improving the flexibility and adaptability of the monitoring work.

[0116] 2) By constructing an optimization model for sampling points, using a 0-1 integer programming solution model, according to the solution results, the number and location of target sampling points in each key sampling area of the target monitoring path are determined. According to the sampling period and the number and location of target sampling points, the first monitoring plan is determined. Through the optimization solution of the optimization model, scientific sampling point positions and numbers can be obtained first, making the first monitoring plan more reasonable.

[0117] 3) Combining historical monitoring data with real-time monitoring results, a water quality change trend prediction model is established to provide a basis for the optimization of subsequent monitoring plans. In this way, potential problems can be predicted in advance to respond to abnormal water quality treatment in a timely manner. In addition, the present invention also introduces a correction model to dynamically adjust the monitoring plan according to the water quality change trend, dynamically changing the number and location of target sampling points to ensure that the monitoring strategy is always in the best state. Through this dynamic adjustment mechanism, the monitoring efficiency can be improved and the operation cost can be reduced, while ensuring the accuracy and reliability of the monitoring results.

[0118] See Figure 2 , in one embodiment, the present invention also provides an online monitoring system for industrial wastewater treatment, and the system includes:

[0119] A candidate path determination unit 100, configured to determine key sampling areas for monitoring at each treatment stage of industrial wastewater according to historical monitoring data, and connect different key sampling areas in sequence according to the order of treatment stages to generate several candidate monitoring paths;

[0120] A target path determination unit 200, configured to determine a reference monitoring path based on historical monitoring cases in the database, perform a correlation analysis on the reference monitoring path and several candidate monitoring paths, and use the candidate monitoring path with the maximum correlation as the target monitoring path for this monitoring;

[0121] The monitoring plan generation unit 300 is configured to build an optimization model for sampling points, solve the model using 0-1 integer programming, determine the quantity and location of target sampling points in each key sampling area in the target monitoring path according to the solution result, and determine a first monitoring plan according to the sampling period and the quantity and location of the target sampling points;

[0122] The monitoring plan adjustment unit 400 is configured to execute the first monitoring plan to obtain the current monitoring result, predict the water quality change trend in each key sampling area according to the historical monitoring data and the current monitoring result, build a correction model according to the water quality change trend, and dynamically adjust the first monitoring plan using the correction model for the monitoring process in the next cycle.

[0123] In one embodiment, the monitoring plan generation unit 300 is further configured to:

[0124] Build the objective function of the optimization model:

[0125] ;

[0126] Determine the constraint conditions:

[0127] ;

[0128] , ;

[0129] ; ;

[0130] In the formula, is the objective function, represents the th key sampling area, and there are a total of ; represents the th sampling point, and there are a total of ; represents the importance weight of the th key sampling area, represents the distance from the th key sampling area to the th sampling point, represents whether the th sampling point is selected, 1 means selected, and 0 means not selected; is the upper limit of the number of sampling points, represents the upper limit of the distance of a single , represents the upper limit of the distance of all ;

[0131] Solve the objective function using 0-1 integer programming to determine the number and location of the target sampling points in each key sampling area.

[0132] In one embodiment, the monitoring scheme adjustment unit 400 is further configured to:

[0133] In the first monitoring scheme, let the initial number of target sampling points in the th key sampling area be , and the position set be , , indicating the initial position of the th target sampling point in the th key sampling area;

[0134] Based on the water quality change trend, obtain the water quality change rate of the th key sampling area within the time as . Then, the adjusted number and position of the target sampling points satisfy the following relationship:

[0135] ;

[0136] ;

[0137] In the formula, represents the updated number of target sampling points, represents the importance weight of the th key sampling area; represents the position of the updated target sampling point, is a random vector representing the offset direction of the target sampling point position; is the natural constant, , are adjustment factors used to adjust the change amplitude of the number and position of the target sampling points respectively, satisfying .

[0138] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the methods described in the above method embodiments. Its specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0139] The present invention also provides an electronic device, including a processor and a memory. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the methods in any of the above possible implementation manners.

[0140] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor is caused to execute the method according to any one of the possible implementation manners described above.

[0141] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. An online monitoring method for industrial wastewater treatment, characterized in that: The method comprises: Determine the key sampling areas for monitoring industrial wastewater at each treatment stage based on historical monitoring data, connect different key sampling areas in sequence according to the order of treatment stages, and generate several candidate monitoring paths; Determine the reference monitoring path based on historical monitoring cases in the database, perform correlation analysis between the reference monitoring path and several candidate monitoring paths, and use the candidate monitoring path with the greatest correlation as the target monitoring path for this monitoring; Construct an optimization model for sampling points, use 0-1 integer programming to solve the model, determine the number and location of target sampling points in each key sampling area in the target monitoring path according to the solution results, and determine the first monitoring plan according to the sampling period and the number and location of the target sampling points; Execute the first monitoring plan to obtain the monitoring results of this monitoring, predict the water quality change trend of each key sampling area based on the historical monitoring data and the monitoring results of this monitoring, build a correction model based on the water quality change trend, and use the correction model to dynamically adjust the first monitoring plan and use it for the next cycle of monitoring process.

2. The online monitoring method for industrial wastewater treatment according to claim 1, characterized in that: The optimization model of the sampling points is constructed by solving the model using 0-1 integer programming, including: Construct the objective function of the optimization model: ； Identify the constraints: ； ， ； ； ； In the formula, is the objective function, Indicates There are a total of key sampling areas indivual; Indicates sampling points, a total of indivual; Indicates The importance weight of each key sampling area, Indicates From the key sampling area to the The distance between sampling points, Indicates Whether the sampling point is selected, 1 means selected, 0 means unselected; is the upper limit of the number of sampling points, Indicates a single The upper limit of the distance Indicates all The upper limit of the distance; The objective function is solved using 0-1 integer programming to determine the number and location of target sampling points in each key sampling area.

3. The online monitoring method for industrial wastewater treatment according to claim 2, characterized in that: The correction model is constructed according to the water quality change trend, including: Assume that in the first monitoring plan, The initial number of target sampling points in the key sampling area is , the location set is , satisfy , Indicates Key sampling areas The initial position of the target sampling points; Based on the water quality change trend, the Key sampling areas in time The water quality change rate is , then it satisfies: ； ； In the formula, represents the updated number of target sampling points, Indicates The importance weight of each key sampling area; represents the updated position of the target sampling point, is a random vector, indicating the offset direction of the target sampling point position; is a natural constant, , are adjustment factors, which are used to adjust the number and position of target sampling points to meet .

4. An online monitoring system for industrial wastewater treatment, characterized in that: The system comprises: A candidate path determination unit is used to determine the key sampling areas for monitoring industrial wastewater at each treatment stage based on historical monitoring data, connect different key sampling areas in sequence according to the order of the treatment stages, and generate a number of candidate monitoring paths; A target path determination unit is used to determine a reference monitoring path based on historical monitoring cases in a database, perform correlation analysis on the reference monitoring path and a number of candidate monitoring paths, and use the candidate monitoring path with the greatest correlation as the target monitoring path for this monitoring; A monitoring scheme generating unit is used to construct an optimization model of sampling points, use 0-1 integer programming to solve the model, determine the number and position of target sampling points in each key sampling area in the target monitoring path according to the solution results, and determine the first monitoring scheme according to the sampling period and the number and position of the target sampling points; The monitoring scheme adjustment unit is used to execute the first monitoring scheme to obtain the monitoring results of this time, predict the water quality change trend of each key sampling area based on historical monitoring data and the monitoring results of this time, build a correction model based on the water quality change trend, and use the correction model to dynamically adjust the first monitoring scheme and use it for the next cycle of monitoring process.

5. The online monitoring system for industrial wastewater treatment according to claim 4, characterized in that: The monitoring scheme generating unit is further used for: Construct the objective function of the optimization model: ； Identify the constraints: ； ， ； ； ； In the formula, is the objective function, Indicates There are a total of key sampling areas indivual; Indicates sampling points, a total of indivual; Indicates The importance weight of each key sampling area, Indicates From the key sampling area to the The distance between sampling points, Indicates Whether the sampling point is selected, 1 means selected, 0 means unselected; is the upper limit of the number of sampling points, Indicates a single The upper limit of the distance Indicates all The upper limit of the distance; The objective function is solved using 0-1 integer programming to determine the number and location of target sampling points in each key sampling area.

6. The online monitoring system for industrial wastewater treatment according to claim 5, characterized in that: The monitoring scheme adjustment unit is further used for: Assume that in the first monitoring plan, The initial number of target sampling points in the key sampling area is , the location set is , satisfy , Indicates Key sampling areas The initial position of the target sampling points; Based on the water quality change trend, the Key sampling areas in time The water quality change rate is , then the adjusted number and position of target sampling points satisfy the following relationship: ； ； In the formula, represents the updated number of target sampling points, Indicates Importance weight of each key sampling area; represents the updated position of the target sampling point, is a random vector, indicating the offset direction of the target sampling point position; is a natural constant, , are adjustment factors, which are used to adjust the number and position of target sampling points to meet .

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program code, wherein the computer program code includes computer instructions, and when the processor executes the computer instructions, the electronic device executes the online monitoring method for industrial wastewater treatment as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the online monitoring method for industrial wastewater treatment according to any one of claims 1 to 3.

Images