Online monitoring method, system, equipment and medium for industrial wastewater treatment

Abstract

The invention discloses an on-line monitoring method, system, equipment and medium for industrial wastewater treatment, and the method comprises the following steps: determining key sampling areas for monitoring each treatment stage of industrial wastewater, and sequentially communicating according to the sequence of the treatment stages to generate candidate monitoring paths; performing correlation analysis on the reference monitoring path and the candidate monitoring path to determine a current target monitoring path; constructing an optimization model, solving by using 0-1 integer programming to determine the position and the number of target sampling points of each key sampling area, and determining a first monitoring scheme in combination with a sampling period; and predicting a water quality change trend of each key sampling area according to historical monitoring data and a current monitoring result, constructing a correction model according to the water quality change trend, and dynamically adjusting the first monitoring scheme for monitoring of a next period. According to the invention, the monitoring path can be flexibly planned, the position and number of the monitoring points can be scientifically selected, the monitoring scheme is dynamically adjusted in combination with historical data, the monitoring efficiency and quality are improved, and the monitoring cost is reduced.

Description

Technical Field

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

[0002] The treatment and discharge of industrial wastewater is one of the important links in the field of environmental protection. In order to ensure that industrial wastewater is effectively treated and meets the national or local emission standards, it is very important 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 shortcomings: 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 failure to promptly detect abnormalities in the treatment process. The number and location of monitoring points are unreasonable. 2) In actual applications, due to the complex and changeable 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) Monitoring path planning is inflexible. Once the monitoring plan is formulated, it cannot be adjusted in time according to actual conditions, making it difficult to quickly respond to abnormal water quality treatment problems, which may miss the best treatment time and affect the overall monitoring quality and energy efficiency. Summary of the invention

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

[0005] In a first aspect, the present invention provides an online monitoring method for industrial wastewater treatment, the method comprising: 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 results of this monitoring, predict the water quality change trend of each key sampling area based on the historical monitoring data and the 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.

[0006] Preferably, 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.

[0007] Preferably, constructing a correction model according to the water quality change trend includes: 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 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 .

[0008] In a second aspect, the present invention further provides an online monitoring system for industrial wastewater treatment, the system comprising: 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.

[0009] Preferably, 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.

[0010] Preferably, 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 .

[0011] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0012] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1) By analyzing historical monitoring data, we can determine the key sampling areas for each processing stage, and use statistical methods such as correlation analysis to select the best path from a large number of 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, we dynamically generate and evaluate different monitoring paths, and select the best path that best meets the current processing conditions, so as to effectively respond to changes in the processing process and improve the flexibility and adaptability of monitoring work.

[0014] 2) By constructing an optimization model of sampling points and using 0-1 integer programming to solve the model, the number and location of target sampling points in each key sampling area in the target monitoring path are determined according to the solution results. The first monitoring plan is determined according to the sampling period and the number and location of target sampling points. The scientific location and number of sampling points can be obtained by optimizing the optimization model, making the first monitoring plan more reasonable.

[0015] 3) Combine historical monitoring data with real-time monitoring results to establish a water quality change trend prediction model to provide a basis for optimizing subsequent monitoring plans. In this way, potential problems can be predicted in advance to respond to abnormal water quality treatment situations 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, so as to dynamically change 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, it is possible to improve monitoring efficiency and reduce operating costs, while ensuring the accuracy and reliability of monitoring results.

[0016] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0019] Figure 1 A schematic diagram of a flow chart of an online monitoring method for industrial wastewater treatment provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of an online monitoring system for industrial wastewater treatment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] In the current monitoring process of industrial wastewater treatment, the selection of the monitored sampling points is often based on manual experience or fixed patterns, and the location and number of the sampling points cannot be reasonably controlled, thereby increasing the monitoring time and cost, and the accuracy and reliability of the monitoring results cannot be guaranteed. To this end, the present invention aims to provide an online monitoring method for industrial wastewater treatment, which can scientifically select a monitoring path for the wastewater treatment stage to ensure that no monitoring link is missed, and then perform optimal solution of the sampling point optimization model based on the monitoring path to scientifically guide the location and number of sampling points of the first scheme; finally, historical data and prediction models are combined to predict the water quality change trend of each sampling area, and a correction model is introduced to dynamically adjust the sampling point selection in the monitoring scheme, thereby greatly improving the monitoring efficiency and the accuracy of the monitoring results, while reducing the monitoring cost.

[0023] See also Figure 1 , Figure 1 A schematic diagram of a process flow of an online monitoring method for industrial wastewater treatment provided by an embodiment of the present invention. Figure 1 As shown, the method includes: S10. 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 several candidate monitoring paths.

[0024] To help understand, first explain the various stages of industrial wastewater treatment: Inlet: The first point where wastewater enters a treatment facility, used to understand the basic characteristics of untreated wastewater, such as pH, temperature, suspended solids (SS), chemical oxygen demand (COD), biochemical oxygen demand (BOD), etc. Pretreatment stage: the screen checks the removal of large particles, the grit chamber evaluates the removal efficiency of inorganic particles, and the regulating tank monitors the stability of water quality and quantity; Primary treatment stage: testing the initial removal effect of suspended matter and changes in organic matter content; Biological treatment stage: Aeration tanks monitor dissolved oxygen levels, microbial activity, ammonia nitrogen conversion rates, etc. to evaluate the effectiveness of the biodegradation process; secondary sedimentation tanks further confirm the improvement in water quality after biological treatment; Advanced treatment stage: coagulation / flocculation reactors observe the aggregation effect of colloids and fine particles; filters test the ability to filter out tiny suspended particles; activated carbon adsorption towers evaluate the adsorption effect on specific pollutants (such as organic matter and heavy metals); Disinfection treatment stage: The disinfection pool ensures that pathogens are effectively killed and meets the requirements for microbial indicators in the emission standards; Final discharge port: The last stage of treatment used to verify the effectiveness of the entire treatment process and ensure that the effluent meets national or local discharge standards.

[0025] In this step, it is first necessary to collect industrial wastewater treatment data over a period of time, such as the past year. These data should include but are not limited to key water quality indicators such as pH, chemical oxygen demand (COD), biochemical oxygen demand (BOD), total suspended solids (TSS), and changes in these indicators at 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 standard. These areas are usually regarded as key sampling areas. For example, if high concentrations of suspended matter are frequently detected in water samples 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 the key sampling area may not be marked because the treatment results are relatively stable, and only conventional monitoring can be used.

[0026] Preferably, when determining the key sampling areas, cluster analysis can be used for rapid screening. For example, the sampling start and end points of each processing stage are determined based on historical sampling data, and clustering is performed separately to form multiple clusters; then the clusters whose cluster center distances are less than the distance threshold are merged to obtain multiple target clusters; finally, it is analyzed which target cluster contains the largest number of start and end points, and the cluster can be marked as the key sampling area.

[0027] Once the key sampling areas for all treatment stages are determined, they can be connected in the order of the wastewater treatment process to form one or more possible monitoring paths. Each path represents a possible monitoring scheme, that is, how to select sampling points for monitoring throughout the entire process from the time the wastewater enters the treatment facility, through a series of treatment units, to the final discharge or reuse.

[0028] S20. Determine a reference monitoring path based on historical monitoring cases in the database, perform correlation analysis on 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.

[0029] In this step, firstly, based on the above historical monitoring data, data cleaning is performed to remove invalid or erroneous data to ensure the accuracy and completeness of the data. Then, according to different wastewater types, treatment processes and treatment scales, the historical monitoring cases are classified to obtain multiple different types of monitoring cases. Then, key features are extracted from each historical monitoring case, such as the location of the sampling point, the changing trend of the monitoring indicators, the order of the treatment stages, etc. Based on the extracted features, a reference monitoring path for each type is constructed. The reference monitoring path should be able to reflect the typical monitoring requirements in the wastewater treatment process of this type.

[0030] Furthermore, correlation analysis is performed for path matching, including matching the generated 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, cosine similarity, etc. can be used to quantify the similarity between the candidate monitoring path and the reference monitoring path. Finally, the candidate monitoring path with the highest correlation is selected as the target monitoring path for this monitoring. If there are multiple paths with the same or close correlation, the path with the lowest cost or highest efficiency can be selected.

[0031] Therefore, the above implementation method first determines the target monitoring path by determining the key sampling area, generating candidate monitoring paths, and then matching the paths, and determines the reference monitoring path through historical monitoring cases to ensure that the selected monitoring path has a scientific basis and can better reflect the key change points in the wastewater treatment process. Based on the analysis and correlation calculation of historical data, the errors 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 maximum correlation, the distribution of sampling points and the sampling frequency can be optimized to reduce the monitoring cost while ensuring the monitoring effect. At the same time, the monitoring path can also be dynamically adjusted to avoid invalid or repeated monitoring and improve the overall efficiency of the monitoring work.

[0032] S30, 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.

[0033] Specifically, 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.

[0034] In the above process, the variables are ,and are known importance weights, is the distance representation of the known sampling points. That is, it is necessary to determine by optimizing the solution After determining which sampling points are selected, the number of target sampling points can be obtained by counting and matching the known Determine the location of the target sampling points. When solving, you only need to input the objective function and constraints into the linear programming software, and you can quickly get the optimal solution by running the solver. After determining the number and location of the target sampling points, you also need to determine the sampling period. Initially, you can refer to historical monitoring data, analyze the trend of water quality changes under different sampling periods, and select a period that can effectively capture water quality changes. At the same time, balance the monitoring cost and monitoring effect, and select a sampling period that can take into account both cost and quality. For example, after this monitoring, determine that the next monitoring time will be one month later.

[0035] This embodiment ensures that the selection of sampling points has a scientific basis by constructing an optimization model, which 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 sampling frequency can be optimized while ensuring the monitoring effect, thereby reducing the monitoring cost.

[0036] S40, execute the first monitoring plan to obtain the monitoring results of this time, predict the water quality change trend of each key sampling area based on the historical monitoring data and the monitoring results of this time, build a correction model based on the water quality change trend, use the correction model to dynamically adjust the first monitoring plan and use it for the next cycle of monitoring process.

[0037] Specifically, predicting the trend of water quality changes includes the following steps: 1) Data preprocessing: Preprocess historical monitoring data and current monitoring results, including data cleaning, missing value processing and outlier detection. Standardize or normalize the data to facilitate subsequent analysis and modeling.

[0038] 2) Trend analysis: Use time series analysis methods, such as ARIMA model and exponential smoothing method, to analyze the historical data and current monitoring results of each key sampling area to identify the changing trend of water quality indicators. Furthermore, visualize the changing trend of water quality, such as drawing time series graphs and trend graphs, to help intuitively understand the law of water quality changes.

[0039] 3) Prediction model construction: Based on the trend analysis results, select appropriate prediction models such as linear regression, neural network, random forest, etc. to predict the trend of water quality changes. The LSTM model is preferably used for prediction.

[0040] Preferably, the training prediction model can be carried out in the following manner: the preprocessed data is used as a training set, feature extraction is performed on the training samples, the extracted features are reduced in dimension using the PCA algorithm, the reduced features are fitted according to the gradient boosting tree algorithm, and the feature quantity with the greatest correlation is screened out from the fitted features; the water quality change rate is fused with the feature quantity with the greatest correlation to train the LSTM model network model with a self-attention mechanism; the loss function is constructed using the root mean square error, and if the value of the loss function is greater than a preset value, the feature quantity with less correlation is screened out from the fitted features, and the fused features are iteratively trained to generate a prediction model until the value of the loss function is less than a preset value.

[0041] In one embodiment, constructing a correction model according to the water quality change trend includes: 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 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 .

[0042] To help understand, we will substitute specific values ​​for explanation below: Assuming that the industrial wastewater treatment process includes three key sampling areas, the initial monitoring plan is as follows: Key sampling area 1: Initial target sampling point number , location set ; Key sampling area 2: Initial target sampling point number , location set ; Key sampling area 3: Initial target sampling point number , location set ; The importance weights of each key sampling area are: , , ; Through historical data and the current monitoring results, the time of each key sampling area is obtained. The water quality change rate is: , , , the regulating factor ; ; ; ; By substituting it into the calculation, we get: , , ; ; ; ; The coordinate units of the position are .

[0043] Therefore, by dynamically adjusting the number of sampling points, it is possible to reduce unnecessary sampling points and reduce monitoring costs while ensuring monitoring results. Dynamically adjusting the sampling point locations can avoid invalid or repeated monitoring and improve the overall efficiency of monitoring work. Combined with the prediction of water quality change trends, the accuracy and reliability of sampling point adjustment can be greatly improved, and monitoring efficiency can be enhanced.

[0044] In one embodiment, in addition to optimizing the location and number of target sampling points, the monitoring period can also be dynamically adjusted, specifically: Determine the period correction factor : ; in, Indicates the preset period correction factor, Indicates the average period of this monitoring. Indicates The monitoring time of key sampling areas is key sampling areas; Indicates target sampling points, a total of target sampling points, Indicates Key sampling areas in time The water quality change rate within It indicates the total number of times the wastewater treatment quality failed to meet the standards at the target sampling points during this monitoring period.

[0045] Finally, multiply the total duration of this cycle by the cycle correction factor The interval to the next monitoring cycle can be determined. This implementation method dynamically adjusts the monitoring cycle according to the water quality change trend and monitoring results, ensuring that the monitoring plan can better reflect water quality changes and improve the accuracy and reliability of monitoring.

[0046] In summary, the method provided by the present invention achieves at least the following beneficial effects: 1) By analyzing historical monitoring data, we can determine the key sampling areas for each processing stage, and use statistical methods such as correlation analysis to select the best path from a large number of 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, we dynamically generate and evaluate different monitoring paths, and select the best path that best meets the current processing conditions, so as to effectively respond to changes in the processing process and improve the flexibility and adaptability of monitoring work.

[0047] 2) By constructing an optimization model of sampling points and using 0-1 integer programming to solve the model, the number and location of target sampling points in each key sampling area in the target monitoring path are determined according to the solution results. The first monitoring plan is determined according to the sampling period and the number and location of target sampling points. The scientific location and number of sampling points can be obtained by optimizing the optimization model, making the first monitoring plan more reasonable.

[0048] 3) Combine historical monitoring data with real-time monitoring results to establish a water quality change trend prediction model to provide a basis for optimizing subsequent monitoring plans. In this way, potential problems can be predicted in advance to respond to abnormal water quality treatment situations 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, so as to dynamically change 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, it is possible to improve monitoring efficiency and reduce operating costs, while ensuring the accuracy and reliability of monitoring results.

[0049] See also Figure 2 In one embodiment, the present invention further provides an online monitoring system for industrial wastewater treatment, the system comprising: The candidate path determination unit 100 is used to determine the key sampling areas for monitoring the industrial wastewater at each treatment stage according to the historical monitoring data, connect the 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 200 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 plurality of candidate monitoring paths, and use the candidate monitoring path with the greatest correlation as the target monitoring path for this monitoring; The monitoring scheme generating unit 300 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 result, 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 400 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.

[0050] In one embodiment, the monitoring scheme generating unit 300 is further configured to: 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.

[0051] In one embodiment, the monitoring scheme adjustment unit 400 is further configured to: 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 .

[0052] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0053] The present invention also provides an electronic device, including a processor and a memory, wherein 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 a method as described in any possible implementation manner.

[0054] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0055] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond 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 results of this monitoring, predict the water quality change trend of each key sampling area based on the historical monitoring data and the 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 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