Urban domestic sewage centralized collection rate prediction method, system and storage medium thereof

Abstract

The present invention provides a method, system and storage medium for predicting the centralized collection rate of urban domestic sewage. The method includes obtaining the land use type within the service area of ​​a sewage treatment plant and selecting a typical plot corresponding to each type of land use attribute; collecting the amount of domestic sewage and the average concentration of sewage pollutants in the typical plot, and calculating the amount of domestic sewage pollution in the typical plot; calculating the statistics of mobile phone signaling data of the typical plot; constructing an RBF neural network with the land use attributes of the plot and the corresponding mobile phone signaling data statistics as input and the predicted amount of domestic sewage pollutants as output, and training to obtain a domestic sewage pollutant prediction model for the plot; using the domestic sewage pollutant prediction model, calculating the predicted value of the centralized collection rate of urban domestic sewage. The present invention associates and analyzes the land use attributes and mobile phone signaling statistics of the plot with the plot pollutant monitoring data, and realizes accurate, real-time and dynamic prediction of the centralized collection rate of urban domestic sewage by constructing a radial basis function (RBF) neural network.

Description

Technical Field

[0001] The invention belongs to the technical field of urban sewage, and in particular relates to a method and system for predicting the centralized collection rate of urban domestic sewage and a storage medium thereof. Background Art

[0002] As my country attaches great importance to urban sewage treatment and resource utilization, the centralized collection rate of urban domestic sewage is a key indicator for evaluating the effectiveness of urban sewage quality improvement and efficiency enhancement and measuring the efficiency of urban sewage treatment. Its accurate calculation is of vital importance.

[0003] The traditional method for calculating the centralized collection rate of urban domestic sewage is:

[0004] The average daily per capita pollutant emissions are usually calculated based on However, this method has many drawbacks. First, the daily per capita pollutant emissions are affected by many factors such as urban residents’ production and lifestyle, living habits, climate conditions, and economic development level. Regional differences are ignored. Secondly, the total population using water in urban areas is generally counted through permanent population data, without considering the dynamic flow of floating population and permanent population between the service areas of different sewage treatment plants, resulting in the service population value not being consistent with the actual situation. The calculation of pure sewage pollution generated by different types of land use has complex spatial asymmetry. These problems combined have led to serious distortions in the prediction results of the centralized collection rate of urban domestic sewage obtained by traditional calculation methods, which cannot provide scientific and accurate support for the work of improving the quality and efficiency of sewage. Summary of the invention

[0005] The purpose of this application is to provide a method, system and storage medium for predicting the centralized collection rate of urban domestic sewage to solve the above-mentioned technical problems.

[0006] According to one aspect of the present application, a method for predicting the centralized collection rate of urban domestic sewage is proposed, the method comprising the following steps:

[0007] S1. Obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes;

[0008] S2. During the monitoring period, collect the amount of domestic sewage and the average concentration of sewage pollutants in typical plots, and calculate the amount of domestic sewage pollution in typical plots;

[0009] Calculate the statistics of mobile phone signaling data of a typical plot during the monitoring period. The statistics of mobile phone signaling data are calculated by superimposing the spatial range of the typical plot and the radiation range corresponding to the associated base station that provides the original mobile phone signaling data;

[0010] S3, constructing an RBF neural network with the land use attributes of the plot and the statistics of mobile phone signaling data corresponding to the plot as input and the predicted amount of domestic sewage pollutants of the plot as output, and training to obtain a domestic sewage pollutant prediction model for the plot;

[0011] S4. Use the domestic sewage pollutant prediction model to obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested, and calculate the predicted value of the centralized collection rate of urban domestic sewage based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested.

[0012] In the above technical solution, the land use attributes and mobile phone signaling statistics of the plots are associated with the plot pollutant monitoring data to construct an RBF neural network model, which can accurately, in real time and dynamically predict the centralized collection rate of urban domestic sewage.

[0013] Furthermore, the drainage system of a typical plot adopts a rainwater and sewage diversion system and there is no sewage mixing, wrong discharge, secret discharge, or leakage. The amount of domestic sewage pollution is expressed as:

[0014]

[0015] in, Expressed as Class land use attributes The amount of domestic sewage pollution in a typical plot during the monitoring period is: Expressed as Class land use attributes The domestic sewage flow rate of a typical plot during the monitoring period is Expressed as Class land use attributes The average concentration of domestic sewage pollutants in a typical plot during the monitoring period is measured in BOD5.

[0016] In the above technical solution, the drainage system of typical plots is strictly limited to a rainwater and sewage diversion system with no sewage mixing, wrong discharge, secret discharge, or leakage. This not only ensures the accuracy and purity of the training data, but also enables the acquired data to truly reflect the actual sewage generation conditions, providing a solid and high-quality data foundation for subsequent model training.

[0017] Furthermore, the calculation steps of the mobile phone signaling data statistics corresponding to the typical plot are as follows:

[0018] S21, obtaining and cleaning the original mobile phone signaling data of all associated base stations whose base station service ranges include the typical plot in the surrounding area of ​​the typical plot during the monitoring period;

[0019] S22, with associated base station Construct Delaunay triangulation for the vertex, generate Thiessen polygons, and determine the associated base station The service range of the typical plot is based on the spatial range and associated base stations. Spatial relationship of the radiation range, calculation of associated base stations The intersection area of ​​typical plots ,in, , It is expressed as the number of associated base stations in the surrounding area of ​​a typical plot;

[0020] S23. Calculate the intersection area The ratio of the total intersection area of ​​the typical plot and each associated base station, based on which the associated base stations are obtained The amount of mobile phone signaling data radiated to a typical plot during the monitoring period;

[0021] S24. Count the amount of mobile phone signaling data radiated by each associated base station in a typical land parcel during a monitoring period, and obtain statistics of mobile phone signaling data of the typical land parcel.

[0022] In the above technical solution, the Thiessen polygon technology is cleverly used to accurately define the spatial relationship between base stations and plots of land, thereby achieving scientific quantification and effective integration of mobile phone signaling data, which greatly improves the availability of data and the rationality of prediction model input.

[0023] Furthermore, the statistics of mobile phone signaling data are expressed as:

[0024]

[0025] in, Represents a plot Statistics of mobile phone signaling data during the monitoring period, Represents a plot Associated with base station The area where the service range intersects, Indicates associated base station The total amount of mobile phone signaling data during the monitoring period, Indicates radiation to the land The total number of all associated base stations, Indicates associated base station The number of all parcels radiated, Represents an index variable used to traverse and calculate the sum, from 1 to Get the value.

[0026] In the above technical solution, the statistical formula of mobile phone signaling data is used to clearly present the relationship between the signaling quantity between base stations and typical plots, providing a key quantitative tool for accurately quantifying the potential impact of mobile phone signaling data on sewage, and significantly improving the scientificity and accuracy of the input data of the prediction model.

[0027] Furthermore, the construction of the RBF neural network includes the following steps:

[0028] S31, input layer setting, using the pre-processed land attribute coding vector of the typical land parcel and the corresponding mobile phone signaling data statistics as the input value of the input neuron;

[0029] S32, hidden layer design, the transformation function in the hidden layer neurons adopts radial basis function, and the output calculation formula of the hidden layer nodes is:

[0030]

[0031] in, Represented as an input vector, namely the land use attributes of a typical plot and the corresponding mobile phone signaling data statistics, Expressed in Euclidean form, is represented as the center of the Gaussian function, Expressed as a smoothing factor, it is used to control the smoothness of the Gaussian function;

[0032] S33, output layer construction, the output layer node output is specifically expressed as:

[0033]

[0034] In the formula, It is represented as the network corresponding to the input sample The output of the output node is the predicted amount of domestic sewage pollutants. , Represented as the number of output nodes, It is represented as the connection weight from the hidden layer to the output layer. , Expressed as the number of hidden layer nodes.

[0035] In the above technical solution, by reasonably setting the parameters and structure of the input layer, hidden layer and output layer, the network can efficiently capture and process complex data characteristics and internal relationships, greatly enhancing the model's fitting ability and prediction accuracy for the predicted amounts of domestic sewage pollutants.

[0036] Furthermore, the training error of the domestic sewage pollutant prediction model uses the cumulative sum of squared errors to determine the optimal parameters, where the sum of squared errors represents:

[0037]

[0038] In the formula, To measure the amount of domestic sewage pollution.

[0039] In the above technical scheme, the cumulative sum of squared errors is used as the training error measurement indicator of the domestic sewage pollutant prediction model, which can comprehensively and deeply evaluate the prediction deviation of the model, and then accurately optimize the model parameters, effectively improving the stability and reliability of the model's prediction results for domestic sewage pollutants in different scenarios.

[0040] Further, step S4 includes:

[0041] S41, obtaining the land use attributes of each domestic sewage producing land parcel to be tested in the service zone of the sewage treatment plant to be tested during the forecast period and calculating the corresponding mobile phone signaling data statistics, using the domestic sewage pollutant prediction model to predict the predicted amount of domestic sewage pollutants in each domestic sewage producing land parcel to be tested during the forecast period, and obtaining the predicted total amount of domestic sewage pollutants in the service zone of the sewage treatment plant to be tested;

[0042] S42. Calculate the predicted value of the centralized collection rate of urban domestic sewage by using the ratio of the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested during the forecast period to the predicted total amount of domestic sewage pollutants.

[0043] In the above technical scheme, the complete process from obtaining the information of the land producing domestic sewage to the final calculation of the predicted value of the centralized collection rate of urban domestic sewage provides a direct and critical data basis for sewage treatment decision-making, and effectively promotes the scientific and refined management process of sewage treatment work.

[0044] In the second aspect, the present application proposes a system for predicting the centralized collection rate of urban domestic sewage, the system comprising:

[0045] A land use analysis module is configured to obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes;

[0046] The training data collection and processing module is configured to collect the amount of domestic sewage and the average concentration of sewage pollutants in the typical plots during the monitoring period, and calculate the amount of domestic sewage pollution in the typical plots respectively; calculate the statistics of mobile phone signaling data of the typical plots during the monitoring period, and the statistics of mobile phone signaling data are calculated by superimposing the spatial range of the typical plots and the radiation range corresponding to the associated base station providing the original mobile phone signaling data;

[0047] The model building and training module is configured to build an RBF neural network with the land use attributes of the plot and the mobile phone signaling data statistics corresponding to the plot as input and the predicted amount of domestic sewage pollutants of the plot as output, and train to obtain the domestic sewage pollutant prediction model of the plot;

[0048] The centralized collection rate prediction module is configured to use the domestic sewage pollutant prediction model to obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested, and calculate the predicted value of the centralized collection rate of urban domestic sewage based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested.

[0049] In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively connected to the processor; when the processor executes computer execution instructions stored in the memory, it is used to implement the method for predicting the centralized collection rate of urban domestic sewage according to the invention content of the first aspect.

[0050] In a fourth aspect, the present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, a method for predicting the centralized collection rate of urban domestic sewage as described in the first aspect of the invention is implemented.

[0051] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the method for predicting the centralized collection rate of urban domestic sewage according to the invention content of the first aspect.

[0052] Compared with the prior art, the beneficial results of the present invention are:

[0053] (1) This application breaks through traditional limitations, deeply integrates the differences of multiple factors, and innovatively introduces mobile phone signaling data and typical plot water quality and quantity monitoring data to construct an RBF neural network. This innovative data association and model construction and training module method breaks the inherent pattern of previous calculation methods, opens up a new path for the calculation of urban domestic sewage centralized collection rate, and greatly enriches the data-driven sewage treatment research ideas and method system.

[0054] (2) This application closely focuses on the core definition and principle of the centralized collection rate of urban domestic sewage, accurately analyzes the shortcomings of traditional methods, and then proposes a scientific process for effectively training RBF neural networks based on monitoring data. This method can accurately capture the dynamic changes in the process of sewage generation and collection, and realize accurate, real-time and dynamic prediction of the centralized collection rate of urban domestic sewage within the service range of a single sewage treatment plant, which has effectively promoted the innovation of technical methods in the sewage treatment industry and significantly improved the industry's technical level and prediction capabilities.

[0055] (3) This application closely meets the urgent need to improve the quality and efficiency of my country's sewage treatment industry. The method for calculating the centralized collection rate of urban domestic sewage constructed comprehensively covers the "pollutant production end", "collection end" and "treatment end" of sewage facilities, providing key indicators for systematic evaluation of the efficiency of sewage facilities. In key engineering practices such as urban rainwater and sewage diversion transformation and sewage pipe network repair and improvement, it can provide practical and feasible scientific guidance, effectively help solve key and difficult problems in the industry, lay a solid foundation for the scientific planning and efficient implementation of urban sewage treatment projects, and promote the sustainable development and optimization and upgrading of urban sewage treatment systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate the embodiments and are used together with the description to explain the principles of the present invention. It will be easy to recognize many expected advantages of the embodiments of the present invention and other embodiments because they become better understood by reference to the following detailed description. The elements of the accompanying drawings are not necessarily to scale with each other. The same reference numerals refer to corresponding similar parts.

[0057] Figure 1 It is a process framework diagram of a method for predicting the centralized collection rate of urban domestic sewage according to an embodiment of the present application;

[0058] Figure 2 a-2b is a schematic diagram of the calculation principle of mobile phone signaling data statistics according to an embodiment of the present application;

[0059] Figure 3 is a schematic diagram of the RBF neural network structure according to an embodiment of the present application;

[0060] Figure 4 It is a process technical circuit diagram of a method for predicting the centralized collection rate of urban domestic sewage according to an embodiment of the present application;

[0061] Figure 5 is a map of the service scope of a treatment plant and the numbering of pollution-generating sites according to an embodiment of the present application;

[0062] Figure 6 is a flow chart of a method for predicting the centralized collection rate of domestic sewage in a certain city according to an embodiment of the present application;

[0063] Figure 7 It is a typical plot monitoring point layout diagram of multiple sewage inspection pipes according to an embodiment of the present application;

[0064] Figure 8 is a diagram of a neural network training error iteration process according to an embodiment of the present application;

[0065] Fig. 9 is a diagram of a hidden layer node number optimization process according to an embodiment of the present application;

[0066] Fig.10 is a diagram of a smoothing factor optimization process according to an embodiment of the present application;

[0067] Fig.11 is a framework diagram of a system for predicting the centralized collection rate of urban domestic sewage according to an embodiment of the present application;

[0068] Fig.12 It is a structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] refer to Figure 1 , Figure 1 The flowchart of the method for predicting the centralized collection rate of urban domestic sewage of the present application is shown. As shown in the figure, the method includes the following steps:

[0071] S101. Obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes.

[0072] In some specific embodiments, the land that produces domestic sewage mainly covers the following 6 types of land attributes: residential land; public management and public service land, specifically including administrative, cultural, educational, sports, health and other facilities land; commercial service facilities land, including commercial land, business land, entertainment and sports land, public facilities business outlets land, etc.; industrial land; logistics and warehousing land; public facilities land, see Table 1 for details. In the process of selecting typical plots, the following professional requirements must be strictly followed: First, for each type of land mentioned above, the number of selected typical plots must not be less than 5 to ensure the richness and representativeness of the sample; second, the drainage system of the selected typical plot must be a complete rainwater and sewage diversion system, and it is strictly forbidden to have rainwater and sewage mixed connection, wrong connection or sewage discharge, leakage and other phenomena, so as to ensure the accuracy and reliability of the data of the selected plots and provide a solid foundation for subsequent related research and analysis.

[0073] Table 1 Classification of typical urban plots

[0074]

[0075] S102. During the monitoring period, the amount of domestic sewage and the average concentration of sewage pollutants of typical plots are collected, and the amount of domestic sewage pollution of the typical plots is calculated respectively; the statistics of mobile phone signaling data of the typical plots during the monitoring period are calculated, and the statistics of mobile phone signaling data are calculated by using the spatial range of the typical plot and the radiation range corresponding to the base station providing the original mobile phone signaling data.

[0076] In some specific embodiments, based on the topological structure characteristics of the sewage pipe network and the municipal sewage pipe network in each typical plot, water quality and water quantity monitoring equipment is accurately set at the front end of the inspection well where the sewage pipe in the building area is connected to the municipal sewage pipe, so as to carry out daily flow Q and five-day biochemical oxygen demand BOD5 monitoring of the typical plot, and the monitoring period shall not be less than 30 days. The water quantity and water quality data obtained daily are defined as a group of data, respectively marked as and (in, Represents the typical land parcel classification number, Represents the data group number, for example: Indicates the 15th group of traffic data for residential land, Indicates the 15th group of BOD5 data for residential land). If a typical plot has multiple sewage discharge pipes that discharge into the municipal sewage pipeline, it is necessary to implement water quality and quantity monitoring operations for each discharge pipe, where the flow rate Q is the sum of the monitored flow rates of all discharge pipes in the typical plot, and the five-day biochemical oxygen demand BOD5 of water quality is the weighted average flow rate of BOD5 of each discharge pipe, so as to ensure the accuracy and comprehensiveness of the monitoring data and provide reliable data support for subsequent related analysis and research. The amount of domestic sewage pollution in each typical plot is expressed as:

[0077]

[0078] in, Expressed as Class land use attributes The amount of domestic sewage pollution in a typical plot during the monitoring period is: Expressed as Class land use attributes The domestic sewage flow rate of a typical plot during the monitoring period is Expressed as Class land use attributes The average concentration of domestic sewage pollutants in a typical plot during the monitoring period is measured in BOD5.

[0079] In some specific embodiments, since typical plots are usually in the form of irregular polygons, based on this, Thiessen polygons are constructed based on the base station positions around the typical plots, and the mobile phone signaling data statistics of each typical plot within the above monitoring period are calculated, wherein the calculation steps of the mobile phone signaling data statistics corresponding to a single typical plot include:

[0080] S1021, obtaining and cleaning the original mobile phone signaling data of all associated base stations whose base station service ranges include the typical plot in the surrounding area of ​​the typical plot during the monitoring period;

[0081] Specifically, we established data acquisition channels with mobile operators such as China Mobile, China Unicom, and China Telecom to obtain the original mobile phone signaling data of all related base stations in the base station service range in the surrounding areas of typical plots during the above monitoring period. Subsequently, we carried out a comprehensive cleaning operation on the acquired original mobile phone signaling data, strictly eliminating all kinds of abnormal values ​​such as those that could not be located, missing information, discontinuous data, and difficult to identify, to ensure the quality and availability of the data and lay a solid foundation for subsequent processing.

[0082] S1022, with associated base station Construct Delaunay triangulation for the vertex, generate Thiessen polygons, and determine the associated base station The service range of the typical plot is based on the spatial range and associated base stations. Spatial relationship of the radiation range, calculation of associated base stations The intersection area of ​​typical plots ,in, , It is expressed as the number of associated base stations in the surrounding area of ​​a typical plot;

[0083] Specifically, first, associate the base station The location is the vertex, and professional geographic information system (GIS) technology and algorithms are used to construct a Delaunay triangulation network, and then generate Thiessen polygons. The area covered by the Thiessen polygon is defined as the corresponding associated base station The service scope of the typical plot is the key spatial scope basis for the subsequent analysis of the relationship between the associated base station and the typical plot. Through careful spatial analysis and calculation, the intersection of the two is determined. This intersection is the effective influence range of the associated base station on the typical plot, providing a spatial basis for further quantifying the influence of the associated base station on the typical plot.

[0084] Furthermore, for all associated base stations Comprehensive statistics of the intersection areas of typical affected plots are made, and their sum, i.e. the intersection area, is calculated. On this basis, the intersection area is calculated The ratio of the total area of ​​all associated base stations to the typical plot is used to accurately quantify the influence of the associated base stations on the typical plot. The degree of influence provides a key proportional parameter for the subsequent calculation of the number of signaling in the intersection part.

[0085] S1023. Calculate the intersection area The ratio of the total intersection area of ​​the typical plot to all associated base stations, based on which the associated base stations are obtained The amount of mobile phone signaling data radiated in a typical area during the monitoring period.

[0086] Specifically, according to the calculated associated base station Intersection area with typical plots The ratio of the total area of ​​intersection between all associated base stations and typical plots is calculated by comparing it with the ratio of the total area of ​​intersection between all associated base stations and typical plots. Multiply the total number of mobile phone signaling recorded during the monitoring period to accurately obtain the associated base stations The amount of mobile phone signaling data radiated to the typical plot during the monitoring period. This step realizes the reasonable allocation and quantitative calculation of the total signaling number of the associated base station to the signaling number of the typical plot, providing accurate data support for in-depth analysis of the mobile phone signaling characteristics of the typical plot.

[0087] S1024. Count the amount of mobile phone signaling data radiated by all associated base stations in a typical land parcel during a monitoring period, and obtain statistics of mobile phone signaling data of the typical land parcel.

[0088] Specifically, the mobile phone signaling data volume of the intersection area between the typical plot and each associated base station service range is summarized and integrated. Through comprehensive and systematic statistical analysis, the mobile phone signaling data statistics of a single typical plot are finally obtained, which can be specifically described by the following formula:

[0089]

[0090] in, Represents a plot Statistics of mobile phone signaling data during the monitoring period, Represents a plot Associated with base station The area where the service range intersects, Indicates associated base station The total amount of mobile phone signaling data during the monitoring period, Indicates radiation to the land The total number of all associated base stations, Indicates associated base station The number of all parcels radiated, Represents the index variable used to traverse the sum calculation, from 1 to Value, used to check the base station in turn All the irradiated plots (total ) and base stations The areas of the intersecting parts of the service range are accumulated and summed up, which is an intermediate variable for auxiliary calculation, similar to a loop counting variable.

[0091] Further references Figure 2 , Figure 2 a-2b shows a schematic diagram of the calculation principle of mobile phone signaling data statistics according to an embodiment of the present application, as shown in Figure 2a, the base station , Base Station , Base Station , Base Station The service coverage of has an intersection area with the typical plot D2. ( Figure 2 a) The green area indicates the base station The area where the service area intersects with the typical plot D2, Indicates base station The total amount of mobile phone signaling data during the monitoring period can be obtained. , , and The calculation method of is similar. Figure 2 b, , , , 、( Figure 2 b) The orange-red areas represent base stations , Base Station , Base Station , Base Station The area of ​​the intersection between the service area and the typical plot D2 is calculated by , , , and base station , Base Station , Base Station , Base Station The total amount of mobile phone signaling data corresponding to the monitoring period , , , , using something like The calculation method is to calculate , and , then the statistics of mobile phone signaling data of the typical plot D2 during the monitoring period are , ,in, , , and Respectively represent base stations , Base Station , Base Station , Base Station The amount of mobile phone signaling data radiated in the typical plot D2 during the monitoring period. It is worth noting that the monitoring period of mobile phone signaling collection needs to be synchronized with the monitoring period of water quality and quantity. The acquired mobile phone signaling data can be divided into two parts, one of which will be used for model training, and this part of the data is referred to as the training set; the other part is used for model testing, and is referred to as the test set accordingly.

[0092] S103, constructing an RBF neural network with the land use attributes of the plot and the mobile phone signaling data statistics corresponding to the plot as input and the predicted amount of domestic sewage pollutants of the plot as output, and training to obtain a domestic sewage pollutant prediction model for the plot.

[0093] In some specific embodiments, reference Figure 3 , Figure 3 A schematic diagram of the RBF neural network structure according to an embodiment of the present application is shown. As shown in the figure, the construction of the RBF neural network includes the following steps:

[0094] S1031, input layer setting, using the pre-processed land use attribute coding vector of the typical land parcel and the corresponding mobile phone signaling data statistics as input values ​​of the input neuron;

[0095] S1032, hidden layer design, the transformation function in the hidden layer neurons adopts radial basis function, and the output calculation formula of the hidden layer nodes is:

[0096]

[0097] in, Represented as an input vector, namely the land use attributes of a typical plot and the corresponding mobile phone signaling data statistics, Expressed in Euclidean form, is represented as the center of the Gaussian function, Expressed as a smoothing factor, it is used to control the smoothness of the Gaussian function;

[0098] S1033, output layer construction, the output layer node output is specifically expressed as:

[0099]

[0100] In the formula, It is represented as the network corresponding to the input sample The output of the output node is the predicted amount of domestic sewage pollutants. , Represented as the number of output nodes, It is represented as the connection weight from the hidden layer to the output layer. , Expressed as the number of hidden layer nodes.

[0101] Specifically, the Radical Basis Function (RBF) neural network is a three-layer forward network, which transforms the input vector through the radial basis function, thereby making the problem that is linearly inseparable in low-dimensional space linearly separable in high-dimensional space. The first layer of the radial basis function neural network is the input layer, which is composed of the input vector source. The middle layer is the hidden layer. The number of nodes in this layer can be flexibly increased or decreased according to the fitting requirements. The transformation function in its neurons is the radial basis function, and the third layer is the output layer. The training of the neural network refers to the process in which the network adjusts the weights and thresholds between nodes based on the prediction error in the training data set. In order to achieve the optimal prediction accuracy of the neural network, parameter optimization operations for different numbers of hidden layer nodes and smoothing factors can be carried out simultaneously during the training process, and the training error can be described by the cumulative sum of squared errors (SSE):

[0102]

[0103] In the formula, To measure the amount of domestic sewage pollution, under the premise of avoiding over-training of the network, the number of hidden layer nodes and smoothing factor that minimizes SSE are returned as network parameters to complete the network training process.

[0104] S104. Utilize the domestic sewage pollutant prediction model to obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested, and calculate the predicted value of the centralized collection rate of urban domestic sewage based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested.

[0105] In some specific embodiments, the step of calculating the predicted value of the centralized collection rate of urban domestic sewage includes:

[0106] S1041. Obtain the land use attributes of each domestic sewage-producing plot to be tested in the service area of ​​the sewage treatment plant to be tested during the prediction period and calculate the corresponding mobile phone signaling data statistics, use the domestic sewage pollutant prediction model to predict the predicted amount of domestic sewage pollutants in each domestic sewage-producing plot to be tested during the prediction period, and obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested.

[0107] Specifically, based on the results of the urban sewage pipe network source tracing and investigation, the service scope of the service area of ​​the sewage treatment plant to be tested is delineated, and the average daily number of mobile phone signals of each domestic sewage-producing area to be tested during the forecast period is counted and recorded as (in For the corresponding The radial basis function (RBF) neural network obtained in S103 is used to predict the average daily pollution output of each domestic sewage-producing land parcel to be tested during the prediction period. Furthermore, the total amount of domestic sewage pollution that can be collected within the service area of ​​the sewage treatment plant to be tested can be predicted as follows:

[0108]

[0109] In the formula, Indicates the service area of ​​the sewage treatment plant to be tested. Class Land Use Attributes The predicted amount of domestic sewage pollutants in the domestic sewage production area to be tested, It is expressed as the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested.

[0110] S1042. Calculate the predicted value of the centralized collection rate of urban domestic sewage by using the ratio of the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested during the prediction period to the predicted total amount of domestic sewage pollutants.

[0111] Specifically, the average daily water volume data of the sewage treatment plant to be tested during the forecast period is used and average daily water quality data , and then calculate the average daily total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested during the forecast period :

[0112]

[0113] in, It is represented by the average daily domestic sewage flow collected by the sewage treatment plant under test during the forecast period. It is expressed as the average daily BOD5 concentration of domestic sewage collected during the forecast period of the sewage treatment plant to be tested. It is expressed as the actual total amount of domestic sewage pollutants collected on average daily basis during the forecast period of the sewage treatment plant under test.

[0114] It can be obtained that the centralized collection rate of urban domestic sewage within the service area of ​​the sewage treatment plant to be tested during the forecast period :

[0115] Continue to refer Figure 4 , Figure 4The flowchart of the method for predicting the centralized collection rate of urban domestic sewage according to one embodiment of the present application is shown, which includes the following steps:

[0116] Step 401: Statistics of land use in sewage treatment plant service areas.

[0117] Step 402: Classification and extraction of typical land plots. The land that generates domestic sewage is divided into six categories: residential land, public management and public service land, commercial service facility land, industrial land, logistics and warehousing land, and public facility land.

[0118] Step 403: water quality and quantity detection of typical plots. First, the five-day biochemical oxygen demand (BOD5) in the sewage of the typical plot is detected and the sewage flow is monitored. According to the BOD5 concentration and sewage flow, the pollutant discharge of the typical plot is calculated, which is the domestic sewage pollution.

[0119] Step 404: Collection of mobile phone signaling data of typical plots. The original signaling data of all base stations in the surrounding area of ​​the typical plots during the monitoring period is obtained from mobile operators such as China Mobile, China Unicom, and China Telecom, and the signaling data is cleaned to remove abnormal values.

[0120] Step 405: Classification and processing of typical land mobile phone signaling, specifically including the following sub-steps:

[0121] S4051: Construct Thiessen polygons, construct Delaunay triangulation with the base station location as the vertex, generate Thiessen polygons, and determine the service range of the base station.

[0122] S4052: Range superposition and cutting: spatially superimpose the spatial range of the typical plot with the base station service range to determine the influence range of the base station on the typical plot.

[0123] S4053: Calculate the intersection ratio, count the sum of the intersection areas of all plots affected by the base station, and calculate the ratio of the typical plot in the sum.

[0124] S4054: Calculate the number of signaling in the intersecting part (i.e., the amount of mobile phone signaling data), and multiply it by the total number of mobile phone signaling on the monitoring day of the base station based on the proportion of the typical plot of land in the area affecting the base station, to obtain the statistical amount of mobile phone signaling data radiated by the base station in the typical plot of land on the monitoring day.

[0125] S4055: Signaling data statistics, counting the number of mobile phone signaling at the intersection of each typical plot and the service range of each base station, and obtaining plot-level statistical results.

[0126] Step 406: construct a radial basis function (RBF) neural network, and input data such as the land use attributes of each typical plot and the pollutant emission of each typical plot into the neural network.

[0127] Step 407: Optimize the hidden layer nodes and weights of the neural network.

[0128] Step 408: Determine whether the minimum mean square error is achieved. If not, return to step 407 to continue optimization; if achieved, execute step 409.

[0129] Step 409: Optimize the smoothing factor.

[0130] Step 410: Determine whether the minimum mean square error is achieved. If not, return to step 409 to continue optimization; if achieved, execute step 411.

[0131] Step 411: Network verification, verifying the optimized neural network to ensure its accuracy and reliability.

[0132] Step 412: Calculate the pollutant emissions of each plot, using the land use attributes of each domestic sewage producing plot to be tested and the mobile phone signaling classification processing data of each domestic sewage producing plot to be tested, and use the verified neural network to calculate the predicted domestic sewage pollutant emissions of each domestic sewage producing plot to be tested.

[0133] Step 413: Calculate the pollution emission of the sewage treatment plant service area, and calculate the actual total emission of domestic sewage pollutants in the sewage treatment plant service area according to the pollutant emission of each domestic sewage producing land to be tested.

[0134] Step 414: Calculate the centralized collection rate of urban domestic sewage, calculate the ratio of the actual total discharge of domestic sewage pollutants to the predicted total discharge of domestic sewage pollutants, and obtain the centralized collection rate of urban domestic sewage, wherein the predicted total discharge of domestic sewage pollutants is the sum of the predicted discharges of domestic sewage pollutants from each domestic sewage-producing area to be tested.

[0135] A typical plot refers to a single plot unit within a given set of typical plots. In the process of model building, directional research or parameter analysis, this single plot is focused on as an independent object and used for the collection and analysis of training data involved in the model. The domestic sewage production plot to be tested is the plot that needs to be analyzed in the actual urban domestic sewage centralized collection rate prediction work after the model is built. In actual application scenarios, its scope is not limited to typical land use types.

[0136] Example

[0137] This article takes a sewage treatment plant as an example to introduce the specific implementation of the present invention. The sewage treatment plant has a capacity of 50,000 m³ / d and serves an urban area of ​​11 km². The sewage treatment plant started construction in March 2010 and was completed and put into operation in October 2011. The specific service scope is shown in Figure 5 . refer to Figure 6 , Figure 6 FIG. 4 is a flow chart showing a method for predicting the centralized collection rate of domestic sewage in a certain city according to the present embodiment. Figure 6 As shown, the prediction method includes:

[0138] Step 1: Conduct a land use analysis on the service area of ​​a sewage treatment plant, select and determine typical plots by category, and obtain typical plots corresponding to each type of land use attributes.

[0139] Specifically, a sewage treatment plant is located in the city center of a certain city. The land used for pollution within its service area mainly includes three types of land use: residential land, public management and public service land, and commercial service facility land. Therefore, in the city center of a certain city, the construction areas that have completed the rainwater and sewage diversion transformation of the above three types of land use attributes are selected as typical plots, with no less than 5 items of each type of land use. Among them, the typical residential land numbers are R D1 , R D2 , R D3 , R D4 , R D5 , the typical public administration and public service land numbers are A D1 , A D2 , A D3 , A D4 , A D5 The typical commercial service facilities land numbers are B D1 , B D2 , B D3 , B D4 , B D5 .

[0140] Step 2: Obtain water quality and quantity monitoring data on the amount of domestic sewage and the average concentration of sewage pollutants in typical plots, and calculate the amount of domestic sewage pollution in various typical plots as training set samples.

[0141] Specifically, according to the topological relationship between the sewage pipe network and the municipal sewage pipe network in each typical plot, water quality and water quantity monitoring equipment is installed in front of the inspection well where the sewage pipe in the building area is connected to the municipal sewage pipe to monitor the daily flow Q and the five-day biochemical oxygen demand BOD5 of the typical plot. The monitoring time is not less than 30 days. The daily water quantity and water quality data are recorded as a set of data, respectively recorded as and ( is the classification number of typical plots, is the data group number). If a typical plot has multiple sewage outflow pipes that discharge into the municipal sewage pipeline, the water quality and quantity of each outflow pipe should be monitored separately. Figure 7The measured flow rate Q is the sum of the monitored flow rates of all discharge pipes, and the five-day biochemical oxygen demand BOD5 of water quality is the weighted average flow rate of BOD5 of each discharge pipe. The amount of domestic sewage pollutants in each typical plot is calculated, specifically:

[0142]

[0143] Expressed as Land use category Monitor the daily pollution output of typical plots; Expressed as Land use category Monitor daily pure sewage flow in typical plots; Expressed as Land use category The average daily concentration of pure sewage (measured in BOD5) was monitored in a typical plot.

[0144] This example selects 30-day monitoring data of a typical plot for analysis, as shown in Tables 2 to 4. Among them, 80% of the data is used for model training, referred to as the training set; 20% of the data is used for model testing, referred to as the test set.

[0145] Table 2 Statistics of water quality and quantity monitoring results in typical residential areas

[0146]

[0147] Table 3 Statistics of water quality and quantity monitoring results of typical public management and public service plots

[0148]

[0149] Table 4 Statistics of water quality and quantity monitoring results for typical commercial service facilities

[0150]

[0151] Step three: collect and process mobile phone signaling from typical plots to obtain a training set of mobile phone signaling data statistics.

[0152] Specifically, based on the base station locations around the typical plots, Thiessen polygons are constructed to obtain the mobile phone signaling data statistics of a single typical plot. The specific steps are as follows:

[0153] (1) Obtain original mobile phone signaling data. Obtain original signaling data of all base stations in the monitoring period in the area around typical plots from mobile operators such as China Mobile, China Unicom, and China Telecom, and clean the signaling data to remove abnormal values ​​such as those that cannot be located, have missing information, are discontinuous, and are difficult to identify.

[0154] (2) Construct Thiessen polygons. Construct a Delaunay triangulation network with the base station location as the vertex, and generate Thiessen polygons, which are the service range of the base station;

[0155] (3) Range superposition and cutting. The spatial range of the typical plot and the base station service range are spatially superimposed, and the intersection is the influence range of the base station on the typical plot;

[0156] (4) Calculate the intersection ratio. Count the sum of the intersection areas of all plots affected by the base station and calculate the area ratio of the typical plot.

[0157] (5) Calculate the number of signaling in the intersecting part. Multiply the area ratio of the typical plot to the affected base station (i.e., the associated base station) by the total number of mobile phone signaling on the monitoring day of the base station to obtain the number of mobile phone signaling radiated by the base station in the typical plot on the monitoring day.

[0158] (6) Signaling data statistics: Count the number of mobile phone signals at the intersection of each typical plot and the service range of each base station to obtain plot-level statistical results.

[0159]

[0160] In the formula, Represents a plot Statistics of mobile phone signaling data during the monitoring period, Represents a plot Associated with base station The area where the service range intersects, Indicates associated base station The total amount of mobile phone signaling data during the monitoring period, Indicates radiation to the land The total number of all associated base stations, Indicates associated base station The number of all parcels radiated, Represents the index variable used for traversal and sum calculation, and the value .

[0161] According to the above steps, the mobile phone signaling data of each typical plot on each monitoring day are calculated respectively. Of the obtained mobile phone signaling data, 80% of the data is used for model training, referred to as the training set; 20% of the data is used for model testing, referred to as the test set. See Tables 5 to 7 for details.

[0162] Table 5 Statistics of mobile phone signaling data in typical residential areas

[0163]

[0164] Table 6 Statistics of mobile phone signaling data in typical public management and public service areas

[0165]

[0166] Table 7 Statistics of mobile phone signaling data for typical commercial service facilities plots

[0167]

[0168] Step 4: construct a radial basis function neural network with the land use attributes of the plot and the corresponding mobile phone signaling data statistics as input and the predicted amount of domestic sewage pollutants of the plot as output, and train it to obtain the domestic sewage pollutant prediction model of the plot.

[0169] Specifically, according to step three and step four, the domestic sewage pollution amounts of at least 5 typical plots of each type of land use and their corresponding mobile phone signaling data statistics are obtained respectively, and randomly divided into training data, verification data and test data in a ratio of 8:1:1, and the data are normalized.

[0170] In MATLAB software, an RBF neural network was constructed with the land use type and mobile phone signaling data statistics as input and the predicted amount of domestic sewage pollution as output, and the network initialization settings were completed.

[0171] During network training, the number of hidden layer nodes and smoothing factor parameters are optimized simultaneously. By setting a reasonable value range and change step size, the network parameters within the value range are substituted into the network training in turn using the enumeration method, and the training error of the neural network under different numbers of hidden layer nodes and smoothing factors is calculated.

[0172] After iteration, the optimal number of hidden layer nodes is determined to be 16 and the smoothing factor is 0.6. The network training process and parameter optimization process are detailed in Figure 8~Figure 10 .

[0173] Step 5: Calculation of the predicted total amount of domestic sewage pollutants within the service area of ​​a sewage treatment plant;

[0174] According to step 3, the average daily number of mobile phone signals for each land use within the service area of ​​a sewage treatment plant during the forecast period is counted and recorded as ( is the corresponding land classification number), and the radial basis function (RBF) neural network obtained in step 4 predicts the average daily domestic sewage pollution of each land use during the prediction period. , see Table 8 for specific forecast data.

[0175] Table 8 Calculation table of the average daily domestic sewage pollution volume predicted for a sewage treatment plant service area

[0176]

[0177] Furthermore, the total amount of pollutants in domestic sewage that can be collected within the service area of ​​the sewage treatment plant to be tested can be predicted. Specifically:

[0178] =8086.4kg / d

[0179] in, Indicates the service area of ​​a sewage treatment plant to be tested. Land use category The average daily domestic sewage pollution volume of the domestic sewage producing areas to be tested, It represents the predicted total amount of pollutants in domestic sewage on an average daily basis within the service area of ​​a sewage treatment plant to be tested.

[0180] Step six: Calculate the predicted value of the centralized collection rate of urban domestic sewage within the service area of ​​a sewage treatment plant.

[0181] Average daily water volume data of a monitored sewage treatment plant during the forecast period The average BOD5 concentration is 42,800 m³ / d. The actual total amount of domestic sewage pollutants collected by the sewage treatment plant on average per day during the forecast period is 128.6 mg / l. :

[0182]

[0183] in, It is expressed as the average daily domestic sewage flow collected by a certain sewage treatment plant during the forecast period; It is expressed as the average daily domestic sewage BOD5 concentration collected during the forecast period of a sewage treatment plant; It is expressed as the actual total amount of average daily domestic sewage pollutants collected by a sewage treatment plant during the forecast period.

[0184] Furthermore, the centralized collection rate of urban domestic sewage within the service area of ​​the sewage treatment plant during the forecast period can be obtained. ,Right now

[0185] Continue to refer Fig.11 As an implementation of the above method, in a second aspect, the present application provides an embodiment of a system 1100 for predicting the centralized collection rate of urban domestic sewage. Figure 1Corresponding to the method embodiment shown, the system can be specifically applied to various electronic devices. The system 1100 includes a land use analysis module 1101, a data acquisition and processing module 1102, a model building and training module 1103 and a concentrated collection rate prediction module 1104 which are interconnected, wherein:

[0186] The land use analysis module 1101 is configured to obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes;

[0187] The data collection and processing module 1102 is configured to collect the amount of domestic sewage and the average concentration of sewage pollutants in the typical plots during the monitoring period, and calculate the amount of domestic sewage pollution in the typical plots respectively; calculate the statistics of mobile phone signaling data of the typical plots during the monitoring period, and the statistics of mobile phone signaling data are calculated by superimposing the spatial range of the typical plots and the radiation range corresponding to the associated base station providing the original mobile phone signaling data;

[0188] The model building and training module 1103 is configured to build an RBF neural network with the land use attributes of the plot and the mobile phone signaling data statistics corresponding to the plot as input and the predicted amount of domestic sewage pollutants of the plot as output, and train to obtain a domestic sewage pollutant prediction model for the plot;

[0189] The centralized collection rate prediction module 1104 is configured to use the domestic sewage pollutant prediction model to obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested, and calculate the predicted value of the centralized collection rate of urban domestic sewage based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested.

[0190] The present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned methods for predicting the centralized collection rate of urban domestic sewage is implemented.

[0191] Reference below Fig.12 , which shows a schematic diagram of the structure of a computer system 1100 of a terminal device or server suitable for implementing an embodiment of the present application. Fig.12 The terminal device or server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0192] like Fig.12As shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage part 1208 into a random access memory (RAM) 1203. In the RAM 1203, various programs and data required for the operation of the computer system 1200 are also stored. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other through a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0193] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed, so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0194] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1209, and / or installed from the removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0195] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0196] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0197] Although the principles of the present invention are described in detail above in conjunction with the preferred embodiments of the present invention, those skilled in the art should understand that the above embodiments are merely explanations of the exemplary implementations of the present invention, and are not intended to limit the scope of the present invention. The details in the embodiments do not constitute limitations on the scope of the present invention, and any obvious changes such as equivalent transformations, simple replacements, etc. based on the technical solution of the present invention, without departing from the spirit and scope of the present invention, fall within the protection scope of the present invention.

Claims

1. A method for predicting the centralized collection rate of urban domestic sewage, characterized in that: The method comprises: S1. Obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes; S2. During the monitoring period, collect the amount of domestic sewage and the average concentration of sewage pollutants in the typical plots, and calculate the amount of domestic sewage pollution in the typical plots; Calculating the statistics of mobile phone signaling data of the typical plot within the monitoring period, wherein the statistics of mobile phone signaling data are obtained by superimposing the spatial range of the typical plot and the radiation range corresponding to the associated base station providing the original mobile phone signaling data; S3, constructing an RBF neural network with the land use attributes of the plot and the corresponding mobile phone signaling data statistics as input and the predicted amount of domestic sewage pollutants of the plot as output, and training to obtain a domestic sewage pollutant prediction model for the plot; S4. Using the domestic sewage pollutant prediction model, the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested is obtained, and based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested, the predicted value of the centralized collection rate of urban domestic sewage is calculated; wherein, The drainage system of the typical plot adopts a rainwater and sewage diversion system and there is no sewage mixing, wrong discharge, secret discharge, or leakage. The amount of domestic sewage pollution is expressed as: in, Expressed as Class land use attributes The amount of domestic sewage pollution in a typical plot during the monitoring period is: Expressed as Class land use attributes The domestic sewage flow rate of a typical plot during the monitoring period is: Expressed as Class land use attributes The average concentration of domestic sewage pollutants in a typical plot during the monitoring period, measured in BOD5; The calculation steps of the mobile phone signaling data statistics corresponding to the typical plot are as follows: S21, obtaining and cleaning the original mobile phone signaling data of all associated base stations in the base station service range in the surrounding area of ​​the typical plot including the typical plot within the monitoring period; S22, with associated base station Construct a Delaunay triangulation network with the vertex at the location, generate Thiessen polygons, and determine the associated base station The service scope of the typical land parcel is used to connect the spatial scope of the typical land parcel to the associated base station. The spatial relationship of the radiation range, calculate the associated base station The intersection area of ​​the typical plots ,in, , It is represented by the number of base stations associated with the surrounding area of ​​the typical plot; S23, calculating the intersection area The ratio of the total intersection area of ​​the typical plot and each associated base station, based on which the associated base station is obtained The amount of mobile phone signaling data radiated to the typical plot during the monitoring period; S24, counting the amount of mobile phone signaling data radiated by each associated base station in the typical land parcel during the monitoring period, and obtaining the statistics of the mobile phone signaling data of the typical land parcel; The mobile phone signaling data statistics are expressed as: In the formula, Represents a plot Statistics of mobile phone signaling data during the monitoring period, Represents a plot Associated with base station The area where the service range intersects, Indicates associated base station The total amount of mobile phone signaling data during the monitoring period, Indicates radiation to the land The total number of all associated base stations, Indicates associated base station The number of all parcels radiated, Represents the index variable used for traversal and sum calculation, and the value .

2. The method for predicting the centralized collection rate of urban domestic sewage according to claim 1, characterized in that: The construction of the RBF neural network includes the following steps: S31, input layer setting, using the pre-processed land use attribute coding vector of the typical land parcel and the corresponding mobile phone signaling data statistics as input values ​​of the input neuron; S32, hidden layer design, the transformation function in the hidden layer neurons adopts radial basis function, and the output calculation formula of the hidden layer nodes is: in, Represented as an input vector, namely the land use attributes of a typical plot and the corresponding mobile phone signaling data statistics, Expressed in Euclidean form, is represented as the center of the Gaussian function, Expressed as a smoothing factor, it is used to control the smoothness of the Gaussian function; S33, output layer construction, the output layer node output is specifically expressed as: In the formula, It is represented as the network corresponding to the input sample The output of the output node is the predicted amount of domestic sewage pollutants. , Represented as the number of output nodes, It is represented as the connection weight from the hidden layer to the output layer. , Expressed as the number of hidden layer nodes.

3. The method for predicting the centralized collection rate of urban domestic sewage according to claim 2, characterized in that: The training error of the domestic sewage pollutant prediction model uses the cumulative error sum of squares to determine the optimal parameters, where the error sum of squares represents: In the formula, To measure the amount of domestic sewage pollution.

4. The method for predicting the centralized collection rate of urban domestic sewage according to claim 1, characterized in that: The S4 step includes: S41, obtaining the land use attributes of each domestic sewage producing land parcel to be tested in the service zone of the sewage treatment plant to be tested during the forecast period and calculating the corresponding mobile phone signaling data statistics, using the domestic sewage pollutant prediction model to predict the predicted amount of domestic sewage pollutants for each domestic sewage producing land parcel to be tested during the forecast period, and obtaining the predicted total amount of domestic sewage pollutants in the service zone of the sewage treatment plant to be tested; S42. Calculate the predicted value of the concentrated collection rate of urban domestic sewage by using the ratio of the actual total amount of domestic sewage pollutants collected by the tested sewage treatment plant during the prediction period to the predicted total amount of domestic sewage pollutants.

5. A system for predicting the centralized collection rate of urban domestic sewage, characterized in that: The system comprises: A land use analysis module is configured to obtain the land use types within the service area of ​​the sewage treatment plant and select typical plots corresponding to each type of land use attributes; The training data collection and processing module is configured to collect the amount of domestic sewage and the average concentration of sewage pollutants of the typical plot within the monitoring period, and respectively calculate the amount of domestic sewage pollution of the typical plot; calculate the statistics of mobile phone signaling data of the typical plot within the monitoring period, and the statistics of mobile phone signaling data are calculated by superimposing the spatial range of the typical plot and the radiation range corresponding to the associated base station providing the original mobile phone signaling data; A model building and training module is configured to build an RBF neural network with the land use attributes of the plot and the corresponding mobile phone signaling data statistics as input and the predicted amount of domestic sewage pollutants of the plot as output, and train to obtain a domestic sewage pollutant prediction model for the plot; The centralized collection rate prediction module is configured to use the domestic sewage pollutant prediction model to obtain the predicted total amount of domestic sewage pollutants in the service area of ​​the sewage treatment plant to be tested, and calculate the predicted value of the centralized collection rate of urban domestic sewage based on the actual total amount of domestic sewage pollutants collected by the sewage treatment plant to be tested; wherein, The drainage system of the typical plot adopts a rainwater and sewage diversion system and there is no sewage mixing, wrong discharge, secret discharge, or leakage. The amount of domestic sewage pollution is expressed as: in, Expressed as Class land use attributes The amount of domestic sewage pollution in a typical plot during the monitoring period is: Expressed as Class land use attributes The domestic sewage flow rate of a typical plot during the monitoring period is: Expressed as Class land use attributes The average concentration of domestic sewage pollutants in a typical plot during the monitoring period, measured in BOD5; The calculation steps of the mobile phone signaling data statistics corresponding to the typical plot are as follows: S21, obtaining and cleaning the original mobile phone signaling data of all associated base stations in the base station service range in the surrounding area of ​​the typical plot including the typical plot within the monitoring period; S22, with associated base station Construct a Delaunay triangulation network with the vertex at the location, generate Thiessen polygons, and determine the associated base station The service scope of the typical land parcel is used to connect the spatial scope of the typical land parcel to the associated base station. The spatial relationship of the radiation range, calculate the associated base station The intersection area of ​​the typical plots ,in, , It is represented by the number of base stations associated with the surrounding area of ​​the typical plot; S23, calculating the intersection area The ratio of the total intersection area of ​​the typical plot and each associated base station, based on which the associated base station is obtained The amount of mobile phone signaling data radiated to the typical plot during the monitoring period; S24, counting the amount of mobile phone signaling data radiated by each associated base station in the typical land parcel during the monitoring period, and obtaining the statistics of the mobile phone signaling data of the typical land parcel; The mobile phone signaling data statistics are expressed as: In the formula, Represents a plot Statistics of mobile phone signaling data during the monitoring period, Represents a plot Associated with base station The area where the service range intersects, Indicates associated base station The total amount of mobile phone signaling data during the monitoring period, Indicates radiation to the land The total number of all associated base stations, Indicates associated base station The number of all parcels radiated, Represents the index variable used for traversal and sum calculation, and the value .

6. An electronic device, characterized in that: The invention comprises a processor and a memory in communication with the processor; the memory stores computer-executable instructions; When the processor executes the computer-executable instructions stored in the memory, it is used to implement the method for predicting the centralized collection rate of urban domestic sewage as described in any one of claims 1 to 4.

7. A computer-readable storage medium, wherein a computer program is stored in the medium, and when the computer program is executed by a processor, the method for predicting the centralized collection rate of urban domestic sewage as described in any one of claims 1 to 4 is implemented.

Images