Intelligent dosing method and system for wastewater treatment based on Internet of Things technology

Abstract

The invention discloses an intelligent dosing method and system for wastewater treatment based on the Internet of Things technology, and relates to the technical field of sewage treatment.The method comprises the following steps that wastewater data are collected from various sensors in a wastewater treatment area based on the Internet of Things technology; simplifying the wastewater treatment scene based on a clustering algorithm, and making a decision rule of intelligent dosing based on the simplified wastewater treatment scene; carrying out gridding treatment on the wastewater treatment area; constructing a dosing demand function, determining a plurality of areas with the maximum dosing demand, and dosing in the plurality of areas with the maximum dosing demand; the system comprises a data collection module, a scene simplification module, a gridding processing module and an area determination module. According to the invention, during intelligent dosing, the complexity of data processing is effectively reduced, the data processing efficiency is improved, the dosing strategy can be dynamically adjusted according to real-time data, and the flexibility and adaptability of wastewater treatment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to an intelligent dosing method and system for wastewater treatment based on Internet of Things technology. Background Art

[0002] The Internet of Things is a technology that connects various devices and systems to achieve data exchange and remote control. In wastewater treatment, various sensors, monitoring equipment and control units are connected through the Internet of Things technology to achieve real-time data collection and interconnection.

[0003] Dosing in wastewater treatment refers to the process of adding chemicals to wastewater during the treatment process. This is to change the physical or chemical properties of the wastewater so that pollutants can be more effectively removed or reduced. Dosing is usually carried out at different stages of wastewater treatment to meet specific treatment goals. For example, pH adjustment, disinfection, phosphorus removal, etc. The dosing process requires precise control of the dosage of the drug to ensure treatment efficiency and economy. With the development of technology, many wastewater treatment plants have begun to adopt automated dosing systems. These systems can automatically adjust the dosage based on real-time monitored wastewater quality data to achieve more accurate and effective wastewater treatment. For example, Chinese patent 201810315713.5 discloses an online dosing control method and system for wastewater treatment, in which the online dosing model is established using principal component analysis algorithm, genetic algorithm and neural network model algorithm, overcoming the defect that it is difficult to accurately determine the dosing dosage in the dosing method during wastewater treatment. However, the above online dosing control method still has the following shortcomings: the method relies on the combination of principal component analysis algorithm, genetic algorithm and neural network model algorithm, and needs to retrain the model for different wastewater treatment scenarios, which may not be flexible and efficient enough when dealing with different or changing wastewater qualities.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes an intelligent dosing method and system for wastewater treatment based on Internet of Things technology to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a smart dosing method for wastewater treatment based on the Internet of Things technology is provided, and the smart dosing method for wastewater treatment based on the Internet of Things technology comprises the following steps: S1. Collect wastewater data from various sensors in the wastewater treatment area based on the Internet of Things technology, and clean the collected wastewater data.

[0007] S2. Simplify the wastewater treatment scenario based on the clustering algorithm, and formulate decision rules for intelligent dosing based on the simplified wastewater treatment scenario.

[0008] S3. Grid the wastewater treatment area and make each dosing point within the grid range.

[0009] S4. Construct a drug addition demand function, determine several areas with the greatest drug addition demand, and perform drug addition in the areas with the greatest drug addition demand.

[0010] Furthermore, in order to simplify the decision-making process, reduce unnecessary complexity, improve the accuracy and efficiency of dosing decisions, reduce operating costs, and ensure wastewater treatment effects: Simplifying the wastewater treatment scenario based on the clustering algorithm and formulating the decision rules for intelligent dosing based on the simplified wastewater treatment scenario include the following steps: S21, normalizing the wastewater data, and forming rows of a sample space matrix with samples of the normalized wastewater data, and forming columns of the sample space matrix with features of the wastewater data; S22, obtaining a normalized matrix using the similarity matrix and the degree matrix; S23, extracting the first two or three eigenvectors of the normalized matrix, and mapping the first two or three eigenvectors into a two-dimensional or three-dimensional space; S24. Use k-means algorithm to perform feature clustering, divide the wastewater data into several different categories, and obtain representative combinations of wastewater quality parameters; S25. Simplify the wastewater treatment scenario according to the representative wastewater quality parameter combination to obtain a typical wastewater treatment scenario; S26. Develop decision rules for intelligent dosing based on typical wastewater treatment scenarios.

[0011] Furthermore, obtaining a normalized matrix using the similarity matrix and the degree matrix includes the following steps: S221, construct a similarity matrix, and each element W in the similarity matrix ij Represents the similarity between sample i and sample j; S222, constructing a degree matrix, wherein the elements on the diagonal of the degree matrix are the sum of the elements in any row of the similarity matrix; S223, obtaining an unnormalized Laplace matrix by calculating the difference between the degree matrix and the similarity matrix; S224. Obtain a normalized matrix using a symmetric normalization calculation formula.

[0012] Furthermore, when the normalized matrix is ​​obtained using the symmetric normalization calculation formula, the symmetric normalization calculation formula is: ; In the formula, represents a normalized matrix; D represents the degree matrix, W represents the similarity matrix; represents the inverse square root matrix of the degree matrix, I Represents the identity matrix.

[0013] Furthermore, in order to locate areas with high dosing demand and ensure maximum dosing effect: Constructing a dosing demand function, and determining several areas with the greatest dosing demand, and performing dosing in the several areas with the greatest dosing demand includes the following steps: S41, defining a dosing requirement function, wherein the dosing requirement function reflects the degree of demand for dosing in each grid area, and obtaining a dosing requirement function plane; S42, obtaining several areas with the largest dosing demand based on the expansion operation; S43, adding medicine in several areas with the greatest demand for adding medicine according to the decision rules of intelligent adding medicine; Wherein, when obtaining the dosing requirement function plane, the dosing requirement function value is calculated for each grid point in the wastewater treatment area to form the dosing requirement function plane.

[0014] Further, obtaining several areas with the greatest dosing demand based on the expansion operation includes the following steps: S421, determining the initial point of dosing according to the wastewater data, and determining the size and shape of the neighborhood of the dosing point expansion; S422, performing an expansion operation on the dosing requirement function plane, and comparing the dosing requirement function value of each grid point with the dosing requirement function value of the grid points in its neighborhood, and taking the maximum dosing requirement function value in the neighborhood to replace the dosing requirement function value of the current grid point; S423, comparing the expanded dosing demand function plane with the original unexpanded dosing demand function plane, extracting several areas with the largest dosing demand, and determining them as dosing points.

[0015] Furthermore, the calculation formula of the dosing demand function value is: ; In the formula, f ( x ) represents the value of the dosing demand function; n represents the number of samples of wastewater data; w i Indicates i The weight of the samples; P i Indicates i The actual measured value of samples, T i Indicates i The target value of samples; g i Represents the deviation calculation function.

[0016] Furthermore, the weights of samples in the calculation formula of the dosing requirement function value were preliminarily set through expert scoring and adjusted through decision analysis.

[0017] Furthermore, the weight of the samples in the calculation formula of the dosing requirement function value is preliminarily set by expert scoring and adjusted by decision analysis method, including the following steps: A decision matrix is ​​constructed, where the rows represent different typical wastewater treatment scenarios and the columns represent different sample parameters; The initial weight of each sample is determined by the expert scoring method, and the decision matrix is ​​multiplied by the initial weight to obtain a weighted decision matrix; Determine an ideal solution and a negative ideal solution, and use Euclidean distance to calculate the distance between the sample parameter value of each typical wastewater treatment scenario and the ideal solution and the negative ideal solution; For each typical wastewater treatment scenario, the relative proximity is obtained by calculating the ratio of the distance between each sample parameter value of the typical wastewater treatment scenario and the negative ideal solution to the sum of the distances between each sample parameter value of the typical wastewater treatment scenario and the ideal solution and the negative ideal solution; The weight of each sample is adjusted according to the relative proximity.

[0018] According to another aspect of the present invention, there is provided an intelligent dosing system for wastewater treatment based on the Internet of Things technology, the intelligent dosing system for wastewater treatment based on the Internet of Things technology comprises a data collection module, a scene simplification module, a grid processing module and a region determination module; wherein the data collection module is connected to the scene simplification module and the grid processing module, and the scene simplification module and the grid processing module are both connected to the region determination module.

[0019] The data collection module is used to collect wastewater data from various sensors in the wastewater treatment area based on the Internet of Things technology, and to clean the collected wastewater data.

[0020] The scenario simplification module is used to simplify the wastewater treatment scenario based on the clustering algorithm and formulate decision rules for intelligent dosing based on the simplified wastewater treatment scenario.

[0021] The grid processing module is used to perform grid processing on the wastewater treatment area and make each dosing point located within the grid range.

[0022] The area determination module is used to construct a drug addition demand function, determine several areas with the greatest drug addition demand, and perform drug addition in the several areas with the greatest drug addition demand.

[0023] The beneficial effects of the present invention are: (1) The present invention provides an intelligent dosing method and system for wastewater treatment based on Internet of Things technology, which effectively reduces the complexity of data processing during intelligent dosing, while retaining typical wastewater treatment scenarios and improving data processing efficiency. The constructed dosing demand function can dynamically adjust the dosing strategy according to real-time data, thereby improving the flexibility and adaptability of wastewater treatment.

[0024] (2) Collecting wastewater data through Internet of Things technology provides an accurate basis for intelligent dosing; by simplifying the wastewater treatment scenarios and formulating decision rules for intelligent dosing based on the simplified wastewater treatment scenarios, and by retaining representative wastewater treatment scenarios, it helps to simplify the decision-making process, reduce unnecessary complexity, improve the accuracy and efficiency of dosing decisions, reduce operating costs, and ensure wastewater treatment effects.

[0025] (3) The present invention defines a dosing demand function and performs an expansion operation on the dosing demand function plane, so that the dosing demand value of each grid point is compared with the dosing demand value of the grid points in its neighborhood, and the maximum value in the neighborhood is taken to replace the value of the current point. The deviation between the wastewater data of several areas with the largest dosing demand and the target value is large, thereby quantifying the dosing demand, ensuring that dosing is carried out in the areas with the largest demand, optimizing resource allocation, locating areas with high dosing demand through spatial operations, and ensuring that the dosing effect is maximized. At the same time, by combining the use of expert scoring and decision analysis methods, the weight of each sample is reasonably formulated, so that the calculation of the dosing demand function value is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 is a flow chart of an intelligent dosing method for wastewater treatment based on Internet of Things technology according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a smart dosing system for wastewater treatment based on Internet of Things technology according to an embodiment of the present invention.

[0028] In the figure: 1. Data collection module; 2. Scene simplification module; 3. Grid processing module; 4. Area determination module. DETAILED DESCRIPTION

[0029] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0031] According to an embodiment of the present invention, an intelligent dosing method and system for wastewater treatment based on Internet of Things technology are provided.

[0032] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a smart dosing method for wastewater treatment based on the Internet of Things technology is provided, and the smart dosing method for wastewater treatment based on the Internet of Things technology includes the following steps: S1. Collect wastewater data such as pH, COD, BOD and other parameters from various sensors in the wastewater treatment area based on the Internet of Things technology, and clean the collected wastewater data, including removing noise, processing missing values, detecting and correcting outliers, etc., to improve data quality, thereby ensuring the accuracy and availability of wastewater treatment data and providing reliable basic data for subsequent analysis.

[0033] Among them, S1 specifically includes the following steps: Sensors deployed in wastewater treatment areas monitor various parameters in wastewater in real time, such as pH, chemical oxygen demand (COD), biological oxygen demand (BOD), etc.

[0034] The sensors send the monitored data to the data collection system.

[0035] The collected wastewater data are subjected to noise removal, missing value processing, outlier detection and correction.

[0036] Verify the cleaned data to ensure that the data quality meets the analysis requirements.

[0037] The cleaned and verified data is stored in a database or data warehouse to provide support for subsequent data analysis and dosing control models.

[0038] S2. Simplify the wastewater treatment scenario based on the clustering algorithm, and formulate decision rules for intelligent dosing based on the simplified wastewater treatment scenario.

[0039] In a further embodiment, simplifying the wastewater treatment scenario based on a clustering algorithm and formulating a decision rule for intelligent dosing based on the simplified wastewater treatment scenario includes the following steps: S21, normalizing the wastewater data, and forming rows of a sample space matrix with samples of the normalized wastewater data, and forming columns of the sample space matrix with features of the wastewater data; S22, obtaining a normalized matrix using the similarity matrix and the degree matrix; S23, extracting the first two or three eigenvectors of the normalized matrix, and mapping the first two or three eigenvectors into a two-dimensional or three-dimensional space; S24. Use the k-means algorithm to perform feature clustering (find the cluster center of the data, representing different wastewater treatment scenarios), divide the wastewater data into several different categories, and obtain representative combinations of wastewater quality parameters; S25. Simplify the wastewater treatment scenario according to the representative wastewater quality parameter combination to obtain a typical wastewater treatment scenario; S26. Develop decision rules for intelligent dosing based on typical wastewater treatment scenarios. For example, if the BOD value of a cluster center is high, the dosage of the biological treatment agent needs to be increased.

[0040] According to the relationship between the parameters of wastewater data and the dosage, a mathematical model or empirical formula is established to calculate the required dosage. When multiple reagents need to be added at the same time, set priorities for different reagents according to the urgency and effect of the treatment. Formulate the order and time interval for adding reagents to ensure the best treatment effect.

[0041] In a further embodiment, obtaining a normalized matrix using a similarity matrix and a degree matrix comprises the following steps: S221, construct a similarity matrix, and each element W in the similarity matrix ab Indicates the similarity between sample a and sample b; S222, constructing a degree matrix, wherein the elements on the diagonal of the degree matrix are the sum of the elements in any row of the similarity matrix; S223, obtaining an unnormalized Laplace matrix by calculating the difference between the degree matrix and the similarity matrix; S224. Obtain a normalized matrix using a symmetric normalization calculation formula.

[0042] In a further embodiment, when the normalized matrix is ​​obtained using a symmetric normalization calculation formula, the symmetric normalization calculation formula is: ; In the formula, represents a normalized matrix; D represents the degree matrix, W represents the similarity matrix; represents the inverse square root matrix of the degree matrix, I Represents the identity matrix.

[0043] S3. Grid the wastewater treatment area and make each dosing point within the grid range.

[0044] Among them, S3 specifically includes the following steps: According to the size and shape of the wastewater treatment area, the entire treatment area is divided into several small grid units. The grids cover the entire treatment area as evenly as possible.

[0045] The size of the grid is determined so that it covers sufficient spatial range while maintaining sufficient resolution for monitoring and control.

[0046] Determine one or more dosing points in each grid. Based on the location of the dosing points, plan the layout of the dosing equipment, including pipelines, pumping stations, and chemical storage facilities.

[0047] S4. Construct a drug addition demand function, determine several areas with the greatest drug addition demand, and perform drug addition in the areas with the greatest drug addition demand.

[0048] In a further embodiment, constructing a medication demand function, determining several areas with the greatest medication demand, and performing medication in the several areas with the greatest medication demand includes the following steps: S41, defining a dosing requirement function, wherein the dosing requirement function reflects the degree of demand for dosing in each grid area, and obtaining a dosing requirement function plane; S42, obtaining several areas with the largest dosing demand based on the expansion operation; S43, adding medicine in several areas with the greatest demand for adding medicine according to the decision rules of intelligent adding medicine; Wherein, when obtaining the dosing requirement function plane, the dosing requirement function value is calculated for each grid point in the wastewater treatment area to form the dosing requirement function plane.

[0049] In a further embodiment, obtaining several areas with the greatest drug addition demand based on the expansion operation includes the following steps: S421. Determine the initial point of dosing based on the wastewater data, and determine the size and shape of the neighborhood where the dosing point expands; specifically, set specific standards for selecting dosing points based on the goals and standards of wastewater treatment. For example, the initial point is selected at a location where the pollutant concentration exceeds the standard. If multiple pollutants exceed the standard, it may be necessary to comprehensively consider the situation of each pollutant and select one or more initial points.

[0050] S422, dilate the dosing requirement function plane, compare the dosing requirement function value of each grid point with the dosing requirement function value of the grid points in its neighborhood, and take the maximum dosing requirement function value in the neighborhood to replace the dosing requirement function value of the current grid point.

[0051] S423, comparing the expanded dosing demand function plane with the original unexpanded dosing demand function plane, extracting several areas with the largest dosing demand, and determining them as dosing points.

[0052] In a further embodiment, the calculation formula of the dosing requirement function value is: ; In the formula, f ( x ) represents the value of the dosing demand function, which represents the overall degree of dosing demand; n represents the number of samples of wastewater data; w i Indicates i The weight of a sample indicates the importance of this parameter in the dosing decision; P i Indicates i The actual measured value of samples, T i Indicates i The target value of samples; g i Represents the deviation calculation function, which is used to calculate the i The deviation between the actual value of a sample and the target value.

[0053] In a further embodiment, the weights of samples in the calculation formula of the dosing requirement function value are preliminarily set by expert scoring and adjusted by decision analysis.

[0054] In a further embodiment, the weight of the samples in the calculation formula of the dosing requirement function value is initially set by expert scoring, and is adjusted by decision analysis method, including the following steps: By collecting various parameter data in wastewater treatment scenarios, a decision matrix is ​​constructed, where the rows represent different typical,wastewater treatment scenarios and the columns represent different sample parameters; The initial weight of each sample is determined by the expert scoring method, and the decision matrix is ​​multiplied by the initial weight to obtain a weighted decision matrix; Determine an ideal solution and a negative ideal solution, and use Euclidean distance to calculate the distance between the sample parameter value of each typical wastewater treatment scenario and the ideal solution and the negative ideal solution; For each typical wastewater treatment scenario, the relative proximity is obtained by calculating the ratio of the distance between each sample parameter value of the typical wastewater treatment scenario and the negative ideal solution to the sum of the distances between each sample parameter value of the typical wastewater treatment scenario and the ideal solution and the negative ideal solution; The weight of each sample is adjusted according to the relative proximity. The higher the proximity of the sample parameters, the greater the weight.

[0055] The ideal solution is a solution composed of the optimal value of each evaluation indicator (i.e., each column in the decision matrix). For benefit-based indicators (the higher the better), the ideal solution is the maximum value of the indicator; for cost-based indicators (the lower the better), the ideal solution is the minimum value of the indicator.

[0056] The negative ideal solution is a solution composed of the worst values ​​of each evaluation index. For benefit-based indicators, the negative ideal solution is the minimum value of the indicator; for cost-based indicators, the negative ideal solution is the maximum value of the indicator.

[0057] like Figure 2 As shown, according to another embodiment of the present invention, an intelligent dosing system for wastewater treatment based on the Internet of Things technology is provided, and the intelligent dosing system for wastewater treatment based on the Internet of Things technology includes a data collection module 1, a scene simplification module 2, a grid processing module 3 and a region determination module 4; wherein the data collection module 1 is connected to the scene simplification module 2 and the grid processing module 3, and the scene simplification module 2 and the grid processing module 3 are both connected to the region determination module 4.

[0058] The data collection module 1 is used to collect wastewater data from various sensors in the wastewater treatment area based on the Internet of Things technology, and clean the collected wastewater data.

[0059] The scenario simplification module 2 is used to simplify the wastewater treatment scenario based on the clustering algorithm, and formulate decision rules for intelligent dosing based on the simplified wastewater treatment scenario.

[0060] The grid processing module 3 is used to perform grid processing on the wastewater treatment area and make each dosing point located within the grid range.

[0061] The area determination module 4 is used to construct a drug addition demand function, determine several areas with the greatest drug addition demand, and perform drug addition in the several areas with the greatest drug addition demand.

[0062] In summary, the intelligent dosing method and system for wastewater treatment based on the Internet of Things technology provided by the present invention effectively reduces the complexity of data processing during intelligent dosing, while retaining typical wastewater treatment scenarios, improving data processing efficiency, and the constructed dosing demand function can dynamically adjust the dosing strategy according to real-time data to improve the flexibility and adaptability of wastewater treatment. Collecting wastewater data through the Internet of Things technology provides an accurate basis for intelligent dosing; by simplifying the wastewater treatment scenario and formulating intelligent dosing decision rules based on the simplified wastewater treatment scenario, by retaining representative wastewater treatment scenarios, it helps to simplify the decision-making process, reduce unnecessary complexity, improve the accuracy and efficiency of dosing decisions, reduce operating costs, and ensure wastewater treatment effects. The present invention defines a dosing demand function and performs an expansion operation on the dosing demand function plane, so that the dosing demand value of each grid point is compared with the dosing demand value of the grid points in its neighborhood, and the maximum value in the neighborhood is taken to replace the value of the current point. The deviation between the wastewater data of several areas with the largest dosing demand and the target value is large, thereby quantifying the dosing demand, ensuring that dosing is performed in the area with the largest demand, optimizing resource allocation, locating the area with high dosing demand through spatial operations, and ensuring that the dosing effect is maximized. At the same time, by combining the use of expert scoring and decision analysis methods, the weight of each sample is reasonably formulated, so that the calculation of the dosing demand function value is more accurate.

[0063] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional charging modules / units in the systems and devices may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0064] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent dosing method for wastewater treatment based on Internet of Things technology, characterized in that: The intelligent dosing method for wastewater treatment based on the Internet of Things technology includes the following steps: S1. Collect wastewater data from various sensors in the wastewater treatment area based on the Internet of Things technology and clean the collected wastewater data; S2. Simplify the wastewater treatment scenario based on the clustering algorithm, and formulate decision rules for intelligent dosing based on the simplified wastewater treatment scenario; S3. Grid the wastewater treatment area and make each dosing point within the grid range; S4. Construct a drug addition demand function, determine several areas with the largest drug addition demand, and perform drug addition in the areas with the largest drug addition demand.

2. According to claim 1, a smart dosing method for wastewater treatment based on Internet of Things technology is characterized in that: The method of simplifying the wastewater treatment scenario based on the clustering algorithm and formulating a decision rule for intelligent dosing based on the simplified wastewater treatment scenario includes the following steps: S21, normalizing the wastewater data, and forming rows of a sample space matrix with samples of the normalized wastewater data, and forming columns of the sample space matrix with features of the wastewater data; S22, obtaining a normalized matrix using the similarity matrix and the degree matrix; S23, extracting the first two or three eigenvectors of the normalized matrix, and mapping the first two or three eigenvectors into a two-dimensional or three-dimensional space; S24. Use k-means algorithm to perform feature clustering, divide the wastewater data into several different categories, and obtain representative combinations of wastewater quality parameters; S25. Simplify the wastewater treatment scenario according to the representative wastewater quality parameter combination to obtain a typical wastewater treatment scenario; S26. Develop decision rules for intelligent dosing based on typical wastewater treatment scenarios.

3. According to claim 2, a smart dosing method for wastewater treatment based on Internet of Things technology is characterized in that: The method of obtaining a normalized matrix using a similarity matrix and a degree matrix comprises the following steps: S221, construct a similarity matrix, and each element W in the similarity matrix ij Represents the similarity between sample i and sample j; S222, constructing a degree matrix, wherein the elements on the diagonal of the degree matrix are the sum of the elements in any row of the similarity matrix; S223, obtaining an unnormalized Laplace matrix by calculating the difference between the degree matrix and the similarity matrix; S224. Obtain a normalized matrix using a symmetric normalization calculation formula.

4. According to claim 3, a smart dosing method for wastewater treatment based on Internet of Things technology is characterized in that: When the normalized matrix is ​​obtained by using the symmetric normalization calculation formula, the symmetric normalization calculation formula is: ； In the formula, represents a normalized matrix; D represents the degree matrix, W represents the similarity matrix; represents the inverse square root matrix of the degree matrix, I Represents the identity matrix.

5. According to claim 4, a smart dosing method for wastewater treatment based on Internet of Things technology is characterized in that: The method of constructing a drug addition demand function, determining several areas with the greatest drug addition demand, and performing drug addition in the several areas with the greatest drug addition demand comprises the following steps: S41, defining a dosing requirement function, wherein the dosing requirement function reflects the degree of demand for dosing in each grid area, and obtaining a dosing requirement function plane; S42, obtaining several areas with the largest dosing demand based on the expansion operation; S43, adding medicine in several areas with the greatest demand for adding medicine according to the decision rules of intelligent adding medicine; Wherein, when obtaining the dosing requirement function plane, the dosing requirement function value is calculated for each grid point in the wastewater treatment area to form the dosing requirement function plane.

6. The intelligent dosing method for wastewater treatment based on Internet of Things technology according to claim 5 is characterized in that: The method of obtaining several areas with the largest dosing demand based on the expansion operation comprises the following steps: S421, determining the initial point of dosing according to the wastewater data, and determining the size and shape of the neighborhood of the dosing point expansion; S422, performing an expansion operation on the dosing requirement function plane, and comparing the dosing requirement function value of each grid point with the dosing requirement function value of the grid points in its neighborhood, and taking the maximum dosing requirement function value in the neighborhood to replace the dosing requirement function value of the current grid point; S423, comparing the expanded dosing demand function plane with the original unexpanded dosing demand function plane, extracting several areas with the largest dosing demand, and determining them as dosing points.

7. The intelligent dosing method for wastewater treatment based on Internet of Things technology according to claim 6 is characterized in that: The calculation formula of the dosing requirement function value is: ； In the formula, f ( x ) represents the value of the dosing demand function; n represents the number of samples of wastewater data; w i Indicates i The weight of the samples; P i Indicates i The actual measured value of samples, T i Indicates i The target value of samples; g i Represents the deviation calculation function.

8. The intelligent dosing method for wastewater treatment based on Internet of Things technology according to claim 7 is characterized in that: The weights of the samples in the calculation formula of the dosing requirement function value are preliminarily set by expert scoring and adjusted by decision analysis.

9. The intelligent dosing method for wastewater treatment based on Internet of Things technology according to claim 8 is characterized in that: The weight of the samples in the calculation formula of the dosing requirement function value is preliminarily set by expert scoring and adjusted by decision analysis method, including the following steps: A decision matrix is ​​constructed, where the rows represent different typical wastewater treatment scenarios and the columns represent different sample parameters; The initial weight of each sample is determined by the expert scoring method, and the decision matrix is ​​multiplied by the initial weight to obtain a weighted decision matrix; Determine an ideal solution and a negative ideal solution, and use Euclidean distance to calculate the distance between the sample parameter value of each typical wastewater treatment scenario and the ideal solution and the negative ideal solution; For each typical wastewater treatment scenario, the relative proximity is obtained by calculating the ratio of the distance between each sample parameter value of the typical wastewater treatment scenario and the negative ideal solution to the sum of the distances between each sample parameter value of the typical wastewater treatment scenario and the ideal solution and the negative ideal solution; The weight of each sample is adjusted according to the relative proximity.

10. An intelligent dosing system for wastewater treatment based on Internet of Things technology, used to implement the intelligent dosing method for wastewater treatment based on Internet of Things technology according to any one of claims 1 to 9, characterized in that: The intelligent dosing system for wastewater treatment based on the Internet of Things technology includes a data collection module, a scene simplification module, a grid processing module and a region determination module; The data collection module is connected to the scene simplification module and the grid processing module, and the scene simplification module and the grid processing module are both connected to the area determination module; The data collection module is used to collect wastewater data from various sensors in the wastewater treatment area based on the Internet of Things technology, and clean the collected wastewater data; The scenario simplification module is used to simplify the wastewater treatment scenario based on a clustering algorithm, and formulate a decision rule for intelligent dosing based on the simplified wastewater treatment scenario; The grid processing module is used to perform grid processing on the wastewater treatment area and make each dosing point within the grid range; The area determination module is used to construct a drug addition demand function, determine several areas with the greatest drug addition demand, and perform drug addition in the several areas with the greatest drug addition demand.

Images