Intelligent detection method of urban sewage based on multidimensional analysis

Abstract

The present invention discloses an intelligent detection method for urban sewage based on multidimensional analysis, which relates to the technical field of sewage detection, including: collecting sewage flow characteristic parameters; collecting urban activity characteristic parameters; performing fusion distribution analysis based on sewage flow characteristic parameters and urban activity characteristic parameters to obtain fusion pollutant distribution information, and performing sewage sampling to obtain a sewage sample sequence; performing sewage component prediction to obtain sewage component prediction results; obtaining multiple pollutant detection schemes based on the sewage component prediction results, detecting a first sewage sample, obtaining a first detection result and first detection adaptability information; obtaining a sewage detection result sequence and a detection scheme set sequence, and analyzing to obtain a sewage detection result. The present invention solves the technical problems that the detection efficiency is low and the true situation of the pollutant content in urban sewage cannot be accurately reflected when the sewage component is detected in the prior art, and achieves the technical effect of improving sewage detection efficiency and pollutant content detection accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage detection, and in particular to an intelligent detection method for urban sewage based on multidimensional analysis. Background Art

[0002] With the acceleration of urbanization and the continuous growth of population, urban sewage treatment has become an increasingly prominent issue. Urban sewage contains a large amount of harmful substances. If it is directly discharged without effective treatment, it will have a serious impact on the environment and human health. Therefore, it is particularly important to conduct accurate and efficient testing of urban sewage.

[0003] However, traditional urban sewage detection methods often have problems such as low detection accuracy, long time consumption, and complex operation. At the same time, as the composition of urban sewage becomes increasingly complex and changeable, traditional detection methods can no longer meet the needs of modern sewage treatment. In particular, when faced with the simultaneous detection and analysis of multiple pollutants, traditional sewage detection methods seem to be stretched. Summary of the invention

[0004] The present application provides an intelligent detection method for urban sewage based on multi-dimensional analysis, which is used to solve the technical problems that the existing technology has low detection efficiency and cannot accurately reflect the actual situation of pollutant content in urban sewage when performing sewage component detection.

[0005] In view of the above problems, the present application provides an intelligent detection method for urban sewage based on multidimensional analysis.

[0006] In a first aspect of the present application, a method for intelligent detection of urban sewage based on multidimensional analysis is provided, the method comprising:

[0007] Collect sewage flow characteristic parameters in the urban sewage pipe; collect urban activity characteristic parameters in the urban area associated with the urban sewage pipe, wherein the urban activity characteristic parameters include economic activity characteristic parameters and residential activity characteristic parameters; conduct fusion distribution analysis of multiple target pollutants based on the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters to obtain fusion pollutant distribution information, select sampling points, conduct multiple urban sewage sampling, and obtain sewage sample sequences; collect multiple historical sewage detection results and multiple historical urban activity characteristic parameters of the urban sewage pipe at multiple historical times, conduct sewage composition prediction, and obtain sewage composition prediction results, wherein the sewage composition prediction results include multiple predicted pollutant content information of multiple target pollutants; according to the sewage composition prediction results, decide to obtain multiple pollutant detection schemes, detect the first sewage sample in the sewage sample sequence, obtain the first detection result, and obtain the first detection adaptability information; according to the first detection adaptability information, modify the multiple pollutant detection schemes, continue to detect the sewage sample sequence, obtain the sewage detection result sequence and the detection scheme set sequence, and analyze and obtain the sewage detection results of the urban sewage pipe.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The present application collects sewage flow characteristic parameters in urban sewage pipes; collects urban activity characteristic parameters in urban areas associated with urban sewage pipes, wherein the urban activity characteristic parameters include economic activity characteristic parameters and residential activity characteristic parameters; performs fusion distribution analysis of multiple target pollutants based on the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters, obtains fusion pollutant distribution information, selects sampling points, performs multiple urban sewage sampling, and obtains sewage sample sequences; collects multiple historical sewage detection results and multiple historical urban activity characteristic parameters of urban sewage pipes at multiple historical times, performs sewage composition prediction, and obtains sewage composition prediction results, wherein the sewage composition prediction results include multiple predicted pollutant content information of multiple target pollutants; based on the sewage composition prediction results, decides to obtain multiple pollutant detection schemes, detects the first sewage sample in the sewage sample sequence, obtains the first detection result, and obtains the first detection adaptability information; based on the first detection adaptability information, modifies the multiple pollutant detection schemes, continues to detect the sewage sample sequence, obtains the sewage detection result sequence and the detection scheme set sequence, and analyzes and obtains the sewage detection results of the urban sewage pipe. The present invention solves the technical problems that the prior art has low detection efficiency and cannot accurately reflect the true situation of pollutant content in urban sewage when conducting sewage composition detection. By collecting multi-dimensional data such as sewage flow characteristics and urban activity characteristics in sewage pipes, in-depth data fusion and analysis are carried out to achieve the technical effect of improving sewage detection efficiency and pollutant content detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0011] Figure 1 A schematic flow chart of an intelligent method for detecting urban sewage based on multidimensional analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] This application provides an intelligent detection method for urban sewage based on multi-dimensional analysis, which is used to solve the technical problems of low detection accuracy and low efficiency in sewage component detection in the existing technology. By collecting multi-dimensional data such as sewage flow characteristics and urban activity characteristics in sewage pipes, in-depth data fusion and analysis are carried out to achieve the technical effect of improving sewage detection efficiency and accuracy.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification and claims 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 server 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 modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment 1

[0016] like Figure 1 As shown, the present application provides an intelligent detection method for urban sewage based on multidimensional analysis, the method comprising:

[0017] Step S100: collecting sewage flow characteristic parameters in the urban sewage pipe;

[0018] In an embodiment of the present application, the sewage flow characteristic parameters include pipeline topology information, sewage flow parameters and sewage flow characteristic parameters.

[0019] When collecting sewage flow characteristic parameters, prepare corresponding sensors, data collectors, and communication equipment according to collection requirements.

[0020] Flow sensors are installed at key locations of sewage pipes, such as the inlet, outlet, and branch points of the pipes, to monitor the flow of sewage in real time. To obtain flow velocity data, flow velocity sensors such as Doppler flowmeters or propeller flowmeters are installed inside the pipes to measure the flow velocity of sewage in the pipes. The pipe topology is obtained through existing engineering drawings or by using underground pipeline detection instruments.

[0021] The collection of sewage flow characteristic parameters is completed through the above process.

[0022] Step S200: collecting urban activity characteristic parameters in the urban area associated with the urban sewage pipe, wherein the urban activity characteristic parameters include economic activity characteristic parameters and residential activity characteristic parameters;

[0023] In the embodiment of the present application, when collecting characteristic parameters of economic activities, the GIS system is used to quickly identify the distribution, type and scale of enterprises in the urban area. Real-time monitoring technology, such as IoT sensors, is used to track indicators such as traffic flow and energy consumption in the area.

[0024] When collecting characteristic parameters of residential activities, the GIS system and census data are used to accurately draw population density distribution maps and identify densely populated areas. Sensors are installed at key sewage outlets to monitor sewage flow and pollutant concentrations in real time.

[0025] Through the above process, the collection of characteristic parameters of urban activities is completed.

[0026] Step S300: performing fusion distribution analysis of multiple target pollutants according to the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters to obtain fusion pollutant distribution information, and selecting sampling points to perform multiple urban sewage sampling to obtain a sewage sample sequence;

[0027] In the embodiment of the present application, the collected sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters are first integrated, and target pollutants that need to be focused on are selected according to historical data and pollutant emission characteristics, such as heavy metals and organic pollutants.

[0028] Through spatial analysis and time series analysis, we can identify the hot spots and time periods of pollutant emissions. When conducting spatial analysis, we use the GIS system to overlay the characteristic parameters of economic activities and residential activities with the topological structure of sewage pipes to identify potential hot spots of pollutant emissions. When conducting time series analysis, we combine the flow and velocity data in the characteristic parameters of sewage flow to analyze the emission of pollutants in different time periods and determine the temporal distribution of pollutants. Finally, we combine spatial distribution with temporal distribution, and use data fusion technology, such as weighted average, to conduct a comprehensive analysis of the distribution of multiple target pollutants to obtain fused pollutant distribution information.

[0029] According to the fused pollutant distribution information, areas with higher or representative pollutant concentrations are selected as sampling points. Multiple urban sewage sampling is carried out at the selected sampling points to obtain a sewage sample sequence.

[0030] Step S400: collecting a plurality of historical sewage detection results and a plurality of historical urban activity characteristic parameters of the urban sewage pipe at a plurality of historical times, performing sewage composition prediction, and obtaining sewage composition prediction results, wherein the sewage composition prediction results include a plurality of predicted pollutant content information of a plurality of target pollutants;

[0031] In the embodiment of the present application, historical sewage detection data is obtained from the monitoring system of the urban sewage treatment plant or the relevant environmental protection department. The historical sewage detection data includes the detection results of multiple historical time points, covering the content of various target pollutants, such as heavy metals, nitrogen, phosphorus, organic matter, etc.

[0032] Collect the characteristic parameters of urban economic activities corresponding to the time of historical sewage detection results from the statistics bureau, water affairs department, enterprise or residential area management office, such as industrial output value, enterprise sewage discharge records, etc. At the same time, collect the characteristic parameters of residential activities, including population data, residents' water consumption, sewage discharge, etc.

[0033] Through the above process, multiple historical sewage detection results and multiple historical urban activity characteristic parameters are obtained.

[0034] Next, we will perform data cleaning and pre-organization on the multiple historical sewage test results and multiple historical urban activity characteristic parameters, and conduct data analysis to analyze the historical sewage test data, identify the changing trends and seasonal patterns of pollutant content, and determine the potential relationship between urban activity characteristic parameters and pollutant content.

[0035] Then, based on the data characteristics and analysis purpose, select the appropriate statistical model or machine learning model for prediction, such as linear regression, support vector machine, neural network, etc.

[0036] The model was trained using historical sewage detection results and historical urban activity characteristic parameters, and the model parameters were optimized through cross-validation and other methods. The prediction performance of the model was evaluated to ensure that it had good generalization ability.

[0037] Collect real-time urban activity data, input real-time urban activity characteristic parameters into the trained prediction model, and obtain sewage composition prediction results. The sewage composition prediction results include multiple predicted pollutant content information of multiple target pollutants, such as the concentration of heavy metals, organic matter, etc.

[0038] Step S500: according to the sewage component prediction result, a plurality of pollutant detection schemes are determined and acquired, a first sewage sample in the sewage sample sequence is detected, a first detection result is obtained, and first detection suitability information is obtained;

[0039] In the embodiment of the present application, based on the sewage composition prediction results, especially the predicted pollutant content information, a detection scheme that can cover these pollutants is selected. According to the detection accuracy requirements, when the predicted content of a certain pollutant is high, a method with higher detection accuracy for the pollutant is selected. At the same time, according to the laboratory's detection capabilities and resources, avoid choosing overly complex or costly detection methods.

[0040] A first sewage sample in a sewage sample sequence is collected, and the first sewage sample is tested according to a decided testing scheme to obtain a first test result, wherein the first test result includes actual test contents of various target pollutants.

[0041] The first detection result is compared with the sewage component prediction result to determine the difference between the two. Based on the determination result, the adaptability information of the detection scheme for the sewage sample is obtained, that is, the first detection adaptability information.

[0042] Step S600: According to the first detection adaptability information, the multiple pollutant detection schemes are modified, and the detection of the sewage sample sequence is continued to obtain a sewage detection result sequence and a detection scheme set sequence, and the sewage detection result of the urban sewage pipe is obtained by analysis.

[0043] In the embodiment of the present application, the first detection suitability information is integrated with the previous sewage composition prediction results, actual detection results and other data by using data integration technology. The integrated data is preprocessed, including data cleaning, conversion and standardization.

[0044] Use data analysis tools, such as pandas and numpy libraries in Python, to analyze the preprocessed data and find out the problems and deviations in the detection scheme. Based on the results of data analysis, identify the problems in the detection scheme, such as insufficient detection accuracy of certain pollutants and inappropriate detection range. Determine the direction and goal of correction, such as improving the detection accuracy of specific pollutants and expanding the detection range.

[0045] If the detection accuracy is insufficient, introduce more advanced detection technology or equipment, such as high-resolution mass spectrometers, atomic absorption spectrometers, etc. If the detection range is inappropriate, adjust the parameters of the detection method or introduce new detection methods to cover a wider range of pollutant types and concentrations. Validate the revised detection plan in a laboratory environment to ensure that it can meet the expected detection accuracy and range requirements.

[0046] Utilize automation technologies such as sensors and pumps to continuously collect sewage samples from urban sewage pipes and perform necessary pretreatment. Apply the revised detection scheme to the pretreated sewage samples for detection. Obtain the detection results using detection equipment and automated data analysis processes. Arrange the detection results of the continuously collected sewage samples in time series to form a continuous sequence of sewage detection results. After each correction of the detection scheme, record the content and reasons for the correction and add them to the detection scheme set sequence to obtain the detection scheme set sequence.

[0047] Finally, according to the detection adaptability information sequence, multiple detection results in the sewage detection result sequence are weighted and calculated to obtain the sewage detection results of the urban sewage pipe.

[0048] Furthermore, step S100 in the method provided in the application embodiment also includes:

[0049] Collect pipeline topology information in urban sewage pipelines;

[0050] Collecting sewage flow parameters of sewage in the urban sewage pipe;

[0051] The sewage flow velocity parameters of the sewage in the urban sewage pipe are collected and combined with the sewage flow parameters and the pipe topology information to serve as sewage flow characteristic parameters.

[0052] In the embodiment of the present application, high-precision equipment such as underground pipeline detectors and geological radars are used to conduct trenchless field detection of the direction, branches, and connection methods of urban sewage pipes to ensure the accuracy of the data. The detailed layout and connection information of the pipelines are obtained by scanning and digitally processing archival materials such as urban planning drawings and sewage pipe design drawings. Geographic information system technology is used to integrate detection data and archival materials to establish a digital sewage pipe topology model.

[0053] Install online flow meters at key points of sewage pipes, such as pump stations and sewage treatment plant water inlets, to monitor and record sewage flow data in real time. To verify the accuracy of online flow meters and obtain flow data in places where automatic monitoring conditions are not available, manual sampling is performed regularly. Use portable flow meters or containers for measurement, and record the measurement time and flow value. By analyzing the inlet flow data of the sewage treatment plant and combining it with the operation data of the sewage treatment plant, the flow of the sewage pipe can be obtained.

[0054] Install a flow meter, such as a Doppler ultrasonic flow meter, in the pipeline to directly measure the flow rate of sewage.

[0055] The collected sewage flow parameters, sewage flow velocity parameters and pipeline topology information are integrated and analyzed using data analysis software such as Excel, SPSS, etc. or a special water management system to obtain characteristic parameters such as the flow path, flow velocity and flow distribution of sewage in the pipeline network. Through the above process, the sewage flow characteristic parameters are obtained.

[0056] Furthermore, step S200 in the method provided in the application embodiment also includes:

[0057] According to the construction data of the urban sewage pipeline, the associated urban areas are divided;

[0058] Acquire enterprise operation scale information, operation location information, population density location and population activity density information within the urban area as economic activity characteristic parameters and residential activity characteristic parameters;

[0059] The economic activity characteristic parameters and the residential activity characteristic parameters are integrated to obtain the urban activity characteristic parameters.

[0060] In the embodiment of the present application, the construction data of urban sewage pipes, including pipe layout, diameter, connection points, etc., are imported through the GIS system, and the sewage pipe network is accurately drawn on the map using these data. Next, different urban service areas are automatically divided according to factors such as the density and direction of the sewage pipe network to obtain related urban areas.

[0061] Through big data analysis, we process the information in the enterprise database, including annual reports and tax returns, and extract relevant information about the enterprise's business scale, such as the number of employees, annual revenue, total assets, etc. At the same time, we use web crawler technology to capture supplementary data from public enterprise information platforms and industry websites. Through the above process, we obtain information on the business scale of enterprises in the urban area.

[0062] By using geographic positioning technology, such as GPS positioning, combined with the address information provided when the enterprise is registered, accurate positioning is performed in the GIS system to obtain the exact location of the enterprise. Through the above process, the business location information is obtained.

[0063] Census data is spatially analyzed using a GIS system to identify densely populated areas. Census data comes from official statistics from government agencies.

[0064] By analyzing mobile phone signaling data, we can track the activity trajectories and aggregation of the population, and thus obtain the population activity density in different areas, that is, the population activity density information.

[0065] The acquired information on business scale, business location, densely populated locations and population activity density within the urban area is used as economic activity characteristic parameters and residential activity characteristic parameters.

[0066] Since the data of economic activities and residential activities come from different sources and have different dimensions and units, these data are first standardized. For example, the scale of business operations is converted into relative indicators, and the density of population activities is converted into a unified metric. Next, the standardized economic activity data and residential activity data are combined through weighted average, principal component analysis, cluster analysis or other statistical methods using data fusion technology to obtain a comprehensive urban activity index. With the help of GIS technology, the spatial distribution of economic activities and residential activities is superimposed on the map to identify overlapping areas with dense economic activities and dense populations, and determine the hot spots and cold spots of urban activities. Finally, based on the fused data, the characteristic parameter indicators of urban activities are constructed. The characteristic parameter indicators of urban activities include the economic activity intensity index, the residential activity density index, the urban vitality index, etc.

[0067] Furthermore, step S300 in the method provided in the application embodiment also includes:

[0068] According to the monitoring data records of the urban sewage pipes, a set of sample sewage flow characteristic parameters, a set of sample economic activity characteristic parameters and a set of sample residential activity characteristic parameters are obtained, and a plurality of sample pollutant distribution information sets of the plurality of target pollutants are obtained;

[0069] Using the sample sewage flow characteristic parameter set, the sample economic activity characteristic parameter set and the sample residential activity characteristic parameter set as input, and using multiple sample pollutant distribution information sets as output, constructing multiple pollutant distribution analysis branches, and obtaining a pollutant distribution analyzer;

[0070] Based on the pollutant distribution analyzer, the sewage flow characteristic parameters, the economic activity characteristic parameters and the residential activity characteristic parameters are analyzed to obtain a plurality of pollutant distribution information of a plurality of target pollutants;

[0071] fusing the plurality of pollutant distribution information to obtain fused pollutant distribution information;

[0072] According to the importance of detecting the multiple target pollutants, multiple pollutant weights are allocated, and based on the multiple pollutant weights, the area with the most concentrated pollutant distribution is calculated and selected in the fused pollutant distribution information to obtain the sampling point.

[0073] In the embodiment of the present application, the characteristic parameters of sewage flow, such as flow rate, flow velocity, flow direction, etc., are obtained through the monitoring data records of urban sewage pipes, and these characteristic parameters are used as a sample sewage flow characteristic parameter set. The sample economic activity characteristic parameter set and the sample residential activity characteristic parameter set are obtained by processing the enterprise database, tax records, census data, etc. through big data analysis technology.

[0074] By monitoring the samples collected by the equipment at different locations in the sewage pipe, the distribution of multiple target pollutants is analyzed and recorded, and a set of pollutant distribution information of multiple samples of multiple target pollutants is obtained.

[0075] Next, for each target pollutant, a pollutant distribution analysis branch is constructed. Each branch is an independent model used to predict the distribution of the pollutant. According to the characteristics of the data and the complexity of the problem, a suitable machine learning algorithm is selected to construct each analysis branch. In this application, a support vector machine is selected to construct the analysis branch.

[0076] Using sample sewage flow characteristic parameters, sample economic activity characteristic parameters and sample residential activity characteristic parameters as input and corresponding sample pollutant distribution information as output, the model of each analysis branch is trained. The prediction performance of the model is optimized by continuously adjusting the parameters and structure of the model. The performance of the trained model is evaluated by cross-validation or other validation methods, including evaluation of the model's accuracy, precision, recall rate and other indicators to ensure that the model has good generalization ability in practical applications. Finally, the trained multiple analysis branches are integrated into a pollutant distribution analyzer.

[0077] The sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters are input into the constructed pollutant distribution analyzer. Through the analysis of the pollutant distribution analyzer, multiple pollutant distribution information of multiple target pollutants is obtained, that is, the concentration and distribution of each pollutant under current conditions are predicted.

[0078] Since different pollutants have different concentration ranges and units, these data are standardized so that the data of different pollutants can be compared and fused on the same scale. Weighted average, fuzzy logic or data fusion algorithm is used to fuse the distribution information of multiple pollutants. The standardized pollutant distribution data is input into the selected fusion algorithm to obtain the fused pollutant distribution information.

[0079] Different weights are assigned to each target pollutant based on its importance and degree of environmental harm. Weights are assigned based on expert judgment, environmental risk assessment standards, or relevant policy requirements. The fused pollutant distribution information is weighted using the assigned weights. Next, the weighted pollutant distribution is analyzed by setting thresholds and using clustering algorithms or hot spot analysis methods to find the areas with the highest pollutant concentrations. In the areas with the highest concentration of pollutants, sampling points are selected based on actual needs, such as monitoring accuracy, resource limitations, etc.

[0080] Furthermore, step S400 in the method provided in the application embodiment also includes:

[0081] Collecting a plurality of historical sewage detection results and a plurality of historical urban activity characteristic parameters of the urban sewage pipeline at a plurality of historical times, wherein each historical sewage detection result includes historical pollutant content information of the plurality of target pollutants;

[0082] Construct a historical sewage detection result sequence and a historical urban activity characteristic parameter sequence;

[0083] Based on the sewage detection data records of urban sewage pipes, a set of sample sewage detection result sequences, a set of sample urban activity characteristic parameter sequences and a set of sample sewage component prediction results are obtained to construct a sewage component predictor;

[0084] The sewage composition predictor is used to predict the sewage composition of the historical sewage detection result sequence and the historical urban activity characteristic parameter sequence to obtain the sewage composition prediction result, which includes multiple predicted pollutant content information of multiple target pollutants.

[0085] In the embodiment of the present application, historical sewage detection results are obtained from the monitoring system of the urban sewage pipe, and the historical sewage detection results include historical pollutant content information of multiple target pollutants, such as heavy metals, organic pollutants, nutrients, etc. The corresponding historical urban activity characteristic parameters are also collected, and the historical urban activity characteristic parameters include industrial wastewater discharge, urban water consumption, etc.

[0086] Clean and organize the collected historical data to ensure the accuracy and completeness of the data. Process missing values, outliers and duplicate values. Arrange the data in chronological order, such as day, week, month, etc., to complete the construction of the historical sewage detection result sequence and the historical urban activity characteristic parameter sequence.

[0087] Collect sewage detection data records from the monitoring system of urban sewage pipes. Sewage detection data records include information such as the content of various pollutants in sewage samples collected at different time points, sampling time, sampling location, etc. The collected data is preprocessed by cleaning, deduplication, filling missing values, etc. to ensure the quality and consistency of the data. The data is divided into continuous sample sequences according to the time series to obtain a set of sample sewage detection result sequences, a set of sample urban activity characteristic parameter sequences, and a corresponding set of sewage component prediction results.

[0088] All sample sequences are divided into training set, validation set and test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. According to the characteristics of the problem and the nature of the data, a suitable machine learning algorithm is selected to construct a sewage composition predictor. In this application, a support vector machine is selected, and the selected algorithm is trained using the training set. The prediction performance of the model is optimized by adjusting the hyperparameters of the model. Techniques such as cross-validation can be used to evaluate the performance of the model under different parameter combinations. Use the validation set to verify the trained model, and adjust the parameters and structure of the model according to the verification results to obtain better prediction performance. Finally, use the test set to evaluate the model, and calculate the various performance indicators of the model, such as accuracy, mean square error, etc., to ensure that the model has good generalization ability in practical applications. The construction of the sewage composition predictor is completed through the above process.

[0089] Finally, the historical sewage detection result sequence and the historical urban activity characteristic parameter sequence are input into the sewage composition predictor to predict the sewage composition and obtain the sewage composition prediction result. The sewage composition prediction result includes multiple predicted pollutant content information of multiple target pollutants.

[0090] Furthermore, according to the sewage component prediction result, a plurality of pollutant detection schemes are determined and acquired, and a first sewage sample in the sewage sample sequence is detected to obtain a first detection result. The method further includes:

[0091] Acquire multiple detection scheme libraries for the multiple target pollutants;

[0092] Obtain a set of information on predicted pollutant contents of multiple samples of multiple target pollutants, combine multiple detection scheme libraries, construct multiple detection scheme decision branches, and obtain a detection scheme decision maker;

[0093] Based on the detection scheme decision maker, making decisions on the multiple predicted pollutant content information to obtain multiple pollutant detection schemes;

[0094] The multiple pollutant detection schemes are used to detect the first sewage sample in the sewage sample sequence to obtain a first detection result, wherein the first detection result includes multiple first pollutant content information of multiple target pollutants.

[0095] In the examples of the present application, multiple detection scheme libraries for multiple target pollutants are obtained from authoritative sources such as environmental protection agencies, scientific research institutes, professional databases, etc. Each detection scheme includes detailed detection methods, required instruments, reagents, operation steps and data processing methods.

[0096] The sewage composition predictor obtains a set of predicted pollutant content information of multiple samples of multiple target pollutants. Based on the set of predicted pollutant content information of the samples, the content range and distribution of different pollutants are determined. According to the type and content range of the pollutants, the predicted information is divided into different intervals or categories.

[0097] For each pollutant content interval or category, the most suitable detection scheme is selected from the detection scheme library. Based on the matching results, a corresponding detection scheme decision branch is constructed for each pollutant content interval or category. Each decision branch can provide the optimal detection scheme for the pollutant content in that interval or category. All constructed detection scheme decision branches are integrated into a unified framework to complete the construction of the detection scheme decider. The detection scheme decider is used to receive the predicted pollutant content information and output the corresponding optimal detection scheme.

[0098] The information of the multiple predicted pollutant contents is input into the detection scheme decision maker, which automatically selects the most suitable detection scheme according to the input predicted data to obtain multiple pollutant detection schemes.

[0099] A random number generator or similar tool is used to randomly select a sample from the sewage sample sequence as the first sewage sample. Multiple pollutant detection schemes are used to detect the first sewage sample in the sewage sample sequence to obtain a first detection result, which includes the type and content of the pollutant.

[0100] Further, obtaining first detection suitability information, the method further includes:

[0101] Based on the detection data records of the multiple target pollutants, multiple sample pollutant content information sets are obtained, multiple sample detection scheme sets are obtained, and multiple sample applicability sets are obtained by evaluation;

[0102] Using the plurality of sample pollutant content information sets, the plurality of sample detection scheme sets and the plurality of sample applicability sets, constructing a plurality of detection applicability analysis branches to obtain a applicability analyzer;

[0103] The suitability analyzer is used to analyze the multiple first pollutant content information and multiple pollutant detection schemes to obtain multiple first suitability information, and first detection suitability information is calculated.

[0104] In the embodiment of the present application, the content information of multiple target pollutants and the corresponding detection schemes are extracted from the detection data records of multiple target pollutants. According to the pollutant content information, multiple sample pollutant content information sets are constructed, each set representing a specific pollutant content situation. At the same time, the detection schemes corresponding to these samples are recorded to form multiple sample detection scheme sets.

[0105] When conducting a suitability assessment, determine the criteria for assessing the suitability of the test solution, such as accuracy, cost-effectiveness, ease of operation, etc. Develop specific evaluation criteria based on actual needs and environmental conditions. Conduct a suitability assessment for each set of sample pollutant content information and the corresponding set of test solutions. Use statistical analysis, expert evaluation, or other evaluation methods to quantitatively score the suitability of each test solution within a specific pollutant content range and obtain multiple sample suitability sets. Each set contains the optimal test solution for a specific pollutant content range and its suitability score.

[0106] Multiple detection suitability analysis branches are constructed using multiple sample pollutant content information sets, detection scheme sets and applicability sets. During construction, multiple sample pollutant content information sets, detection scheme sets and applicability sets are divided into training sets and verification data sets. Each analysis branch corresponds to a specific pollutant content range and detection scheme combination, and can recommend the optimal detection scheme based on the input pollutant content information. When constructing the detection suitability analysis branch, machine learning algorithms such as decision trees, random forests, and neural networks are used to construct the analysis branch. In this application, a decision tree is selected to construct the analysis branch. The model is trained using the training set so that it can predict the optimal detection scheme based on the pollutant content information. An independent verification data set is used to verify the accuracy of the analysis branch. The construction of the detection suitability analysis branch is completed through the above process, and finally the constructed multiple analysis branches are integrated into a suitability analyzer.

[0107] A suitability analyzer is used to analyze multiple first pollutant content information and multiple pollutant detection schemes. The suitability analyzer evaluates the suitability of each detection scheme based on preset suitability evaluation criteria, such as accuracy, cost-effectiveness, and ease of operation, and outputs the suitability evaluation results of each detection scheme for each first pollutant content information, that is, multiple first suitability information.

[0108] Finally, all the first suitability information is integrated, and the first detection suitability information is calculated by weighted average or fuzzy comprehensive evaluation.

[0109] Furthermore, according to the first detection suitability information, the plurality of pollutant detection schemes are modified, and the detection of the sewage sample sequence is continued. The method further includes:

[0110] Determining whether the plurality of first suitability information meets a suitability threshold, and if so, not modifying the plurality of pollutant detection schemes;

[0111] If not, adjusting and correcting the detection accuracy of the pollutant detection scheme according to the plurality of first applicability information to obtain a plurality of corrected pollutant detection schemes;

[0112] Using the multiple modified pollutant detection schemes, continue to perform detection and adjust the pollutant detection schemes, obtain a sewage detection result sequence and a detection scheme set sequence, and obtain a detection adaptability information sequence;

[0113] According to the detection adaptability information sequence, a plurality of detection results in the sewage detection result sequence are weightedly calculated to obtain the sewage detection result of the urban sewage pipe.

[0114] In the embodiment of the present application, a suitability threshold is first set. The suitability threshold is set by technical experts based on actual needs and experience, and is used to determine whether the suitability of the detection scheme meets the standard.

[0115] Each first suitability information is compared with a set suitability threshold. If all the first suitability information is higher than or equal to the set threshold, it means that the current pollutant detection scheme is good enough and does not need to be modified.

[0116] When any of the first suitability information does not meet the suitability threshold, analyze the first suitability information to determine the specific cause of the problem. Specific reasons include inaccuracy of the detection method, aging or failure of the equipment, improper sampling method, etc. According to the analysis results, determine the part of the detection scheme that needs to be improved. For detection schemes with insufficient detection accuracy, introduce more advanced detection technologies or methods to improve accuracy. If equipment performance is the problem, replace the equipment. Or adjust the sampling strategy to ensure that the collected samples are more representative and reduce sampling errors. After adjustment, multiple corrected pollutant detection schemes are obtained.

[0117] The revised pollutant detection scheme is adopted to continue the sewage detection and further adjust the scheme. In this process, the sewage detection result sequence and the corresponding detection scheme set sequence are obtained, and the applicability information is obtained through the applicability analyzer and the detection adaptability information sequence is obtained through weighted calculation.

[0118] When weighted calculation is performed on multiple test results in the sewage test result sequence according to the test suitability information sequence, the adaptability and accuracy of each test scheme under different conditions are first determined according to the test suitability information sequence. A weight factor is assigned to each test result according to the test suitability information. Test results with high adaptability and accuracy will be given higher weights. Each sewage test result is multiplied by its corresponding weight factor, all weighted test results are added together, and divided by the sum of the weight factors to obtain the weighted average sewage test result, that is, the sewage test result of the urban sewage pipe is obtained.

[0119] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0120] The present application collects sewage flow characteristic parameters in urban sewage pipes; collects urban activity characteristic parameters in urban areas associated with urban sewage pipes, wherein the urban activity characteristic parameters include economic activity characteristic parameters and residential activity characteristic parameters; performs fusion distribution analysis of multiple target pollutants based on the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters, obtains fusion pollutant distribution information, selects sampling points, performs multiple urban sewage sampling, and obtains sewage sample sequences; collects multiple historical sewage detection results and multiple historical urban activity characteristic parameters of urban sewage pipes at multiple historical times, performs sewage composition prediction, and obtains sewage composition prediction results, wherein the sewage composition prediction results include multiple predicted pollutant content information of multiple target pollutants; based on the sewage composition prediction results, decides to obtain multiple pollutant detection schemes, detects the first sewage sample in the sewage sample sequence, obtains the first detection result, and obtains the first detection adaptability information; based on the first detection adaptability information, modifies the multiple pollutant detection schemes, continues to detect the sewage sample sequence, obtains the sewage detection result sequence and the detection scheme set sequence, and analyzes and obtains the sewage detection results of the urban sewage pipe. The present invention solves the technical problems that the prior art has low detection efficiency and cannot accurately reflect the true situation of pollutant content in urban sewage when conducting sewage composition detection. By collecting multi-dimensional data such as sewage flow characteristics and urban activity characteristics in sewage pipes, in-depth data fusion and analysis are carried out to achieve the technical effect of improving sewage detection efficiency and pollutant content detection accuracy.

[0121] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. This specification and the drawings are merely exemplary illustrations of the present application and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. An intelligent detection method for urban sewage based on multidimensional analysis, characterized in that: The method comprises: Collect the sewage flow characteristic parameters in the urban sewage pipe; Collecting urban activity characteristic parameters in the urban area associated with the urban sewage pipe, wherein the urban activity characteristic parameters include economic activity characteristic parameters and residential activity characteristic parameters; According to the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters, a fusion distribution analysis of multiple target pollutants is performed to obtain fusion pollutant distribution information, and sampling points are selected to perform multiple urban sewage sampling. Obtaining sewage sample sequences; Collecting multiple historical sewage detection results and multiple historical urban activity characteristic parameters of the urban sewage pipeline at multiple historical times, predicting sewage composition, and obtaining sewage composition prediction results, wherein the sewage composition prediction results include multiple predicted pollutant content information of multiple target pollutants; According to the sewage component prediction result, a plurality of pollutant detection schemes are determined and acquired, a first sewage sample in the sewage sample sequence is detected, a first detection result is obtained, and first detection suitability information is obtained; According to the first detection suitability information, the multiple pollutant detection schemes are modified, the detection of the sewage sample sequence is continued, a sewage detection result sequence and a detection scheme set sequence are obtained, and the sewage detection result of the urban sewage pipe is obtained by analysis; Among them, the sewage flow characteristic parameters in the urban sewage pipe are collected, including: Collect pipeline topology information in urban sewage pipelines; Collecting sewage flow parameters of sewage in the urban sewage pipe; Collecting sewage flow velocity parameters of sewage in the urban sewage pipe, and combining the sewage flow parameters and the pipe topology information as sewage flow characteristic parameters; The collection of characteristic parameters of urban activities in the urban area associated with the urban sewage pipe includes: According to the construction data of the urban sewage pipeline, the associated urban areas are divided; Acquire enterprise operation scale information, operation location information, population density location and population activity density information within the urban area as economic activity characteristic parameters and residential activity characteristic parameters; Integrate the economic activity characteristic parameters and the residential activity characteristic parameters to obtain urban activity characteristic parameters; According to the sewage flow characteristic parameters, economic activity characteristic parameters and residential activity characteristic parameters, a fusion distribution analysis of multiple target pollutants is performed to obtain fusion pollutant distribution information, including: According to the monitoring data records of the urban sewage pipes, a set of sample sewage flow characteristic parameters, a set of sample economic activity characteristic parameters and a set of sample residential activity characteristic parameters are obtained, and a plurality of sample pollutant distribution information sets of the plurality of target pollutants are obtained; Using the sample sewage flow characteristic parameter set, the sample economic activity characteristic parameter set and the sample residential activity characteristic parameter set as input, and using multiple sample pollutant distribution information sets as output, constructing multiple pollutant distribution analysis branches, and obtaining a pollutant distribution analyzer; Based on the pollutant distribution analyzer, the sewage flow characteristic parameters, the economic activity characteristic parameters and the residential activity characteristic parameters are analyzed to obtain a plurality of pollutant distribution information of a plurality of target pollutants; fusing the plurality of pollutant distribution information to obtain fused pollutant distribution information; According to the importance of the detection of the multiple target pollutants, multiple pollutant weights are assigned, and according to the multiple pollutant weights, the area with the most concentrated pollutant distribution is selected by calculation in the fused pollutant distribution information to obtain the sampling point; The process of collecting a plurality of historical sewage detection results and a plurality of historical urban activity characteristic parameters of the urban sewage pipe at a plurality of historical times to predict the sewage composition includes: Collecting a plurality of historical sewage detection results and a plurality of historical urban activity characteristic parameters of the urban sewage pipeline at a plurality of historical times, wherein each historical sewage detection result includes historical pollutant content information of the plurality of target pollutants; Construct a historical sewage detection result sequence and a historical urban activity characteristic parameter sequence; Based on the sewage detection data records of urban sewage pipes, a set of sample sewage detection result sequences, a set of sample urban activity characteristic parameter sequences and a set of sample sewage component prediction results are obtained to construct a sewage component predictor; The sewage composition predictor is used to predict the sewage composition of the historical sewage detection result sequence and the historical urban activity characteristic parameter sequence to obtain the sewage composition prediction result, wherein the sewage composition prediction result includes a plurality of predicted pollutant content information of a plurality of target pollutants; Wherein, according to the sewage component prediction result, a decision is made to obtain multiple pollutant detection schemes, and the first sewage sample in the sewage sample sequence is detected to obtain a first detection result, including: Acquire multiple detection scheme libraries for the multiple target pollutants; Obtain a set of information on predicted pollutant contents of multiple samples of multiple target pollutants, combine multiple detection scheme libraries, construct multiple detection scheme decision branches, and obtain a detection scheme decision maker; Based on the detection scheme decision maker, making decisions on the multiple predicted pollutant content information to obtain multiple pollutant detection schemes; Using the multiple pollutant detection schemes, detect a first sewage sample in the sewage sample sequence to obtain a first detection result, wherein the first detection result includes multiple first pollutant content information of multiple target pollutants; The obtaining of the first detection suitability information includes: Based on the detection data records of the multiple target pollutants, multiple sample pollutant content information sets are obtained, multiple sample detection scheme sets are obtained, and multiple sample applicability sets are obtained by evaluation; Using the plurality of sample pollutant content information sets, the plurality of sample detection scheme sets and the plurality of sample applicability sets, constructing a plurality of detection applicability analysis branches to obtain a applicability analyzer; The suitability analyzer is used to analyze the multiple first pollutant content information and multiple pollutant detection schemes to obtain multiple first suitability information, and first detection suitability information is calculated.

2. The method according to claim 1, characterized in that According to the first detection suitability information, the plurality of pollutant detection schemes are modified, and the detection of the sewage sample sequence is continued, including: Determining whether the plurality of first suitability information meets a suitability threshold, and if so, not modifying the plurality of pollutant detection schemes; If not, adjusting and correcting the detection accuracy of the pollutant detection scheme according to the plurality of first applicability information to obtain a plurality of corrected pollutant detection schemes; Using the multiple modified pollutant detection schemes, continue to perform detection and adjust the pollutant detection schemes, obtain a sewage detection result sequence and a detection scheme set sequence, and obtain a detection adaptability information sequence; According to the detection adaptability information sequence, a plurality of detection results in the sewage detection result sequence are weightedly calculated to obtain the sewage detection result of the urban sewage pipe.

Images