Method, system, equipment, storage medium and program product for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry

Abstract

The application relates to the technical field of urban sewage discharge management, and discloses a rainwater and sewage mixing detection and tracing method, system, equipment, storage medium and program product based on time-of-flight mass spectrometry, which are used to solve the technical problems of great detection and tracing difficulty and slow speed in the prior art. The method comprises the following steps: obtaining a first detection result of volatile organic compounds of an in-situ time-of-flight mass spectrometer at a first detection position along a drainage pipe network, and inputting the first detection result into a trained mixing judgment model to determine whether mixing exists; if mixing exists, searching for each drainage pipe network detection well in the upstream according to path direction information of the drainage pipe network to obtain at least one second detection position; obtaining a second detection result of volatile organic compounds of an in-situ time-of-flight mass spectrometer at each second detection position; inputting each second detection result into the trained mixing judgment model in a sequence from the downstream to the upstream to perform mixing judgment, searching for a detection well with the mixing condition in the uppermost upstream, and obtaining a mixing point.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban sewage discharge management, and in particular to a rain and sewage mixed connection detection and tracing method, system, device, storage medium and program product based on time-of-flight mass spectrometry. BACKGROUND

[0002] In the past drainage system, the mode of rainwater and sewage sharing a drainage pipeline, that is, the combined drainage system, is often adopted. However, under the demand of environmental protection, urban construction in recent years requires the implementation of rain and sewage separation, and in the process of urban renewal, the original combined drainage system is gradually transformed into a rain and sewage separation system.

[0003] Under this background, the investigation and reconstruction of "rain and sewage mixed connection" is a topic of concern in recent years. "Rain and sewage mixed connection" refers to the phenomenon of incorrect connection between rainwater pipe network and sewage pipe network during the initial construction and urban renewal construction of urban drainage pipe network. Such incorrect connection phenomenon will cause sewage to be discharged into urban water bodies through rainwater pipe network, pollute the environment and even form black and odorous water bodies, or cause a large amount of rainwater to flow into the sewage treatment plant during rainfall, exceeding the treatment capacity of the sewage treatment plant, impacting the sewage treatment system and increasing the operation cost. Therefore, it is crucial to establish a precise and reliable rain and sewage mixed connection investigation technology method for the governance of urban black and odorous water bodies and the safe and stable operation of the sewage discharge management system.

[0004] Currently, the investigation of rain and sewage mixed connection mainly relies on pipeline endoscopic detection technology (CCTV, etc.) and water quality tracing technology based on water quality parameters (such as ammonia nitrogen, COD) or three-dimensional fluorescence spectrum. However, these methods require detection of each well, which is time-consuming and labor-intensive, and has high requirements for on-site water level and other conditions, with great detection difficulty and long feedback cycle. It is urgent to develop a new type of drainage pipe network mixed connection detection and tracing method to realize rapid and intelligent mixed connection point identification and pollution source tracing. SUMMARY

[0005] The main purpose of the present application is to solve the technical problems of great difficulty and slow speed in detecting and tracing the rain and sewage mixed connection of the drainage pipe network in the prior art.

[0006] The first aspect of the present application provides a method for detecting and tracing rainwater and sewage mixing in a drainage network based on time-of-flight mass spectrometry, comprising: obtaining a first detection result of volatile organic compounds at a first detection position along the drainage network by an in-situ time-of-flight mass spectrometer; inputting the first detection result into a trained mixing judgment model to determine whether there is mixing at the first detection position; if there is mixing at the first detection position, finding each drainage network detection well upstream of the first detection position according to path direction information of the drainage network to obtain at least one second detection position; obtaining a second detection result of volatile organic compounds at each second detection position by an in-situ time-of-flight mass spectrometer; inputting each second detection result into the trained mixing judgment model in order from downstream to upstream based on the path direction information of the drainage network to find the detection well at the most upstream in each detection well with mixing, and obtain a mixing point of the drainage network.

[0007] Optionally, in the first implementation manner of the first aspect of the present application, after obtaining the mixing point of the drainage network, the method further comprises: collecting a third detection result of volatile organic compounds at the detection well upstream of the mixing point of the drainage network by an in-situ time-of-flight mass spectrometer, and respectively obtaining a volatile organic compound feature of domestic sewage around the mixing point of the drainage network and a volatile organic compound feature of industrial wastewater around the mixing point of the drainage network; calling a mixing ratio algorithm to solve the fitting according to the third detection result, the volatile organic compound feature of domestic sewage around the mixing point of the drainage network, and the volatile organic compound feature of industrial wastewater around the mixing point of the drainage network, to obtain the type of sewage and the mixing ratio of sewage at the current mixing point.

[0008] Optionally, in the second implementation manner of the first aspect of the present application, before obtaining the first detection result of volatile organic compounds at the first detection position along the drainage network by an in-situ time-of-flight mass spectrometer, the method further comprises: obtaining water samples under multiple mixing ratio conditions, and performing water quality detection and volatile organic compound detection by a time-of-flight mass spectrometer on the water samples to obtain multiple sample mass spectrum detection data; marking a water sample type label on each preprocessed sample mass spectrum detection data, and performing feature selection according to different feature selection methods; using the result after feature selection and the corresponding water sample type label information to train an initial machine learning model to obtain a trained mixing judgment model.

[0009] Optionally, in a third implementation form of the first aspect of the present application, the sample mass spectrum detection data comprises first sample mass spectrum detection data and second sample mass spectrum detection data; the obtaining of the water body samples under different mixing ratios and the water quality detection and the volatile organic compound detection of the water body samples by the time-of-flight mass spectrometer comprise: obtaining a sewerage network geographic information system map in a detection range, and determining a residential area sewage well, an industrial area sewage well, and a non-mixing end rainwater well according to the sewerage network geographic information system map to obtain a plurality of sample detection wells; performing in-situ volatile organic compound detection of the sample detection wells by the time-of-flight mass spectrometer to obtain the first sample mass spectrum detection data, and collecting the water body samples; dividing the water body samples into first-type water samples and second-type water samples, directly detecting the water quality of the first-type water samples to obtain water quality parameters, dividing the second-type water samples into several portions, mixing the second-type water samples with third-type water samples after being cultured at different temperatures, and performing volatile organic compound detection of the mixed water samples by the time-of-flight mass spectrometer to obtain the second sample mass spectrum detection data.

[0010] Optionally, in a fourth implementation form of the first aspect of the present application, the feature selection according to the different feature selection methods comprises: associating water quality parameters of the same sample with sample mass spectrum detection data, and preliminarily screening candidate features according to a dynamic correlation degree; supplementing and verifying the preliminarily screened candidate features based on a pre-constructed water quality field knowledge base; and optimizing the supplemented and verified preliminarily screened candidate features by using a self-adaptive algorithm to obtain a final feature set, thereby completing the selection of the features.

[0011] Optionally, in a fifth implementation form of the first aspect of the present application, the initial machine learning model uses a support vector machine as an initial rain and sewage identification algorithm; and the training of the constructed initial machine learning model by using the results after the feature selection and corresponding water sample type label information to obtain a trained mixing judgment model comprises: generating a training set by using the results after the feature selection and the corresponding water sample type label information, constructing a hyperplane of the support vector machine; calculating distances of sample points in the training set to the hyperplane, introducing a Lagrange multiplier method to obtain a hyperplane with the farthest sample to the hyperplane, making distances between points closest to the hyperplane in different categories of samples and the hyperplane maximum, and updating hyperparameters of the model; generating a test set based on the results after the feature selection and the corresponding water sample type label information, and testing the model after the updating of the hyperparameters by calling the test set, and obtaining the trained mixing judgment model when an accuracy rate of a test result meets a test requirement.

[0012] The second aspect of the present application provides a rain and sewage mixing detection and tracing system based on a time-of-flight mass spectrometer, comprising:

[0013] a data acquisition module configured to acquire a first detection result of volatile organic compounds at a first detection position along the drainage pipe network by using an in-situ time-of-flight mass spectrometer;

[0014] a mixed connection detection module configured to input the first detection result into the trained mixed connection judgment model to determine whether the first detection position has a mixed connection condition;

[0015] a mixed connection tracing module configured to, if the first detection position has a mixed connection condition, find each drainage pipe network detection well upstream of the first detection position according to path direction information of the drainage pipe network to obtain at least one second detection position, acquire a second detection result of volatile organic compounds at each second detection position by using an in-situ time-of-flight mass spectrometer, input each second detection result into the trained mixed connection judgment model in a downstream-to-upstream order based on the path direction information of the drainage pipe network to find a detection well at the most upstream among the detection wells having a mixed connection condition, and obtain a mixed connection point of the drainage pipe network.

[0016] In a third aspect, the present application provides a time-of-flight mass spectrometry-based drainage pipe network rain and sewage mixed connection detection and tracing device, which comprises a memory and at least one processor, and the memory stores instructions.

[0017] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions, and when the instructions are executed on a computer, the computer executes the steps of the time-of-flight mass spectrometry-based drainage pipe network rain and sewage mixed connection detection and tracing method.

[0018] In a fifth aspect, the present application provides a computer program product, which comprises computer programs / instructions, and when the computer programs / instructions are executed by a processor, the steps of the time-of-flight mass spectrometry-based drainage pipe network rain and sewage mixed connection detection and tracing method are implemented.

[0019] The technical scheme provided by the application comprises the following steps: obtaining a first detection result of volatile organic compounds at a first detection position along a drainage pipe network by using an in-situ time-of-flight mass spectrometer; inputting the first detection result into a trained mixed connection judgment model to determine whether the first detection position has a mixed connection condition; if the first detection position has a mixed connection condition, searching for each drainage pipe network detection well upstream of the first detection position according to path direction information of the drainage pipe network to obtain at least one second detection position; obtaining a second detection result of volatile organic compounds at each second detection position by using an in-situ time-of-flight mass spectrometer; inputting each second detection result into the trained mixed connection judgment model in a downstream-to-upstream order based on the path direction information of the drainage pipe network to determine a mixed connection condition, searching for a detection well at the most upstream in each detection well having the mixed connection condition, and obtaining a mixed connection point of the drainage pipe network. The method can realize detection and tracing of rainwater and sewage mixed connection in the drainage pipe network, thereby realizing rapid and intelligent mixed connection point identification and pollution source tracing. The system, electronic equipment, computer readable storage medium and computer program product provided by the application also solve the corresponding technical problems. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application, and do not limit the application. In the drawings:

[0021] Figure 1 A flowchart of a first embodiment of a rainwater and sewage mixed connection detection and tracing method based on a time-of-flight mass spectrometer in the embodiments of the application;

[0022] Figure 2 A flowchart of a second embodiment of a rainwater and sewage mixed connection detection and tracing method based on a time-of-flight mass spectrometer in the embodiments of the application;

[0023] Figure 3 A selection method diagram for selecting model variables in the second embodiment of the rainwater and sewage mixed connection detection and tracing method based on a time-of-flight mass spectrometer in the embodiments of the application;

[0024] Figure 4 A drainage pipe network path diagram in a third embodiment of the rainwater and sewage mixed connection detection and tracing method based on a time-of-flight mass spectrometer in the embodiments of the application;

[0025] Figure 5 A time-of-flight mass spectrometer detection mass spectrum diagram of Q1 effluent of a chemical enterprise in the third embodiment of the rainwater and sewage mixed connection detection and tracing method based on a time-of-flight mass spectrometer in the embodiments of the application;

[0026] Figure 6A time-of-flight mass spectrometry detection mass spectrum of Q2 effluent of a chemical enterprise in a third embodiment of the rain and sewage mixed connection detection and tracing method of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0027] Figure 7 A time-of-flight mass spectrometry detection mass spectrum of Q3 effluent of a chemical enterprise in a third embodiment of the rain and sewage mixed connection detection and tracing method of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0028] Figure 8 A time-of-flight mass spectrometry detection mass spectrum of upstream water in a third embodiment of the rain and sewage mixed connection detection and tracing method of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0029] Figure 9 A time-of-flight mass spectrometry detection mass spectrum of downstream effluent in a third embodiment of the rain and sewage mixed connection detection and tracing method of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0030] Figure 10 A GIS schematic diagram of a municipal sewer system in a fourth embodiment of the rain and sewage mixed connection detection and tracing method of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0031] Figure 11 An embodiment schematic diagram of the rain and sewage mixed connection detection and tracing system of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0032] Figure 12 Another embodiment schematic diagram of the rain and sewage mixed connection detection and tracing system of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0033] Figure 13 An embodiment schematic diagram of the rain and sewage mixed connection detection and tracing equipment of a sewer network based on time-of-flight mass spectrometry in the embodiments of the present application;

[0034] Figure 14 A principle schematic diagram of a computer readable medium in the embodiments of the present application. DETAILED DESCRIPTION

[0035] Exemplary embodiments of the present application will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that the present application will be thorough and complete, and fully convey the inventive concept to those skilled in the art. In the drawings, the same reference numerals are used to represent the same elements, components, or parts throughout the drawings, and thus repeated description thereof will be omitted.

[0036] In the premise of conforming to the technical concept of the present application, the features, structures, characteristics or other details described in a certain specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0037] In the description of specific embodiments, the features, structures, characteristics or other details described in the present application are to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that one or more of the skilled in the art can practice the technical solution of the present application without a specific feature, structure, characteristic or other detail.

[0038] The flowchart shown in the accompanying drawings is only an exemplary illustration, and does not necessarily include all contents and operations / steps, nor does it necessarily execute in the order described. For example, some operations / steps can be further decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

[0039] The block diagram shown in the accompanying drawings is only a functional entity, and does not necessarily correspond to a physically independent entity. That is, these functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0040] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0041] The present application mainly relates to a drainage pipe network rain and sewage mixing detection and tracing method, system, electronic device, computer storage medium and computer program product based on proton transfer reaction-time of flight mass spectrometry. Among them, the "proton transfer reaction-time of flight mass spectrometry" in the present application scheme refers to Proton Transfer Reaction-Time of Flight Mass Spectrometer (abbreviated as PTR-TOF-MS), hereinafter referred to as "time of flight mass spectrometry".

[0042] Please refer to Figure 1 The first embodiment of the drainage pipe network rain and sewage mixing detection and tracing method based on time of flight mass spectrometry in the embodiment of the present application comprises:

[0043] S101, obtaining a first detection result of volatile organic compounds of an in-situ time of flight mass spectrometer at a first detection position along the drainage pipe network;

[0044] The embodiment specifically relates to the field of rain and sewage mixed connection checking technology of urban drainage pipe networks. It can be understood that the execution subject of the application can be a rain and sewage mixed connection detection and tracing system based on time-of-flight mass spectrometry, and can also be a device terminal, which is not limited here.

[0045] In order to quickly and intelligently identify the wastewater properties in the inspection well, the mixed connection judgment model based on the machine learning model is pre-trained in the embodiment, and the mixed connection judgment model is called to determine the actual mixed connection state according to the data information of the water samples at each detection position along the drainage pipe network.

[0046] In the embodiment, the data information of the water samples mainly uses the detection data of volatile organic compounds (VOCs) of in-situ time-of-flight mass spectrometry (TOFMS). According to the difference of volatile organic compounds between rainwater and sewage, the wastewater properties in the inspection well are identified through the high-resolution and rapid detection capability of time-of-flight mass spectrometry, so as to achieve the purpose of judging the wastewater state and category.

[0047] In a specific embodiment in the embodiment, a first detection position along the drainage pipe network in a range to be subjected to rain and sewage mixed connection checking is determined, and a first detection result of volatile organic compounds of in-situ time-of-flight mass spectrometry at the first detection position is obtained. In the embodiment, the core meaning of “in-situ” is to directly detect in the field. The volatile organic compounds of the water samples or headspace gases in the well can be directly detected by using a portable or mobile time-of-flight mass spectrometer in the field of the selected drainage pipe inspection well or rainwater well, without the need of transporting the samples back to the laboratory for measurement. The in-situ detection process can maximize the reduction of the loss, degradation, pollution or concentration change of volatile organic compounds of the samples in the transportation and storage process.

[0048] In S102, the first detection result is input into the trained mixed connection judgment model to perform mixed connection judgment, and it is determined whether the first detection position exists mixed connection.

[0049] After obtaining the first detection result, the trained mixed connection judgment model is called to perform judgment, and it is determined whether the first detection result exists mixed connection. If the mixed connection judgment model judges that the water sample at the first detection position along the drainage pipe network contains more than one water well property based on the first detection result, that is, the water body discharged in the drainage pipe network contains not only rainwater but also sewage, it is determined that the first detection position exists mixed connection.

[0050] S103, if the first detection position exists a mixed connection situation, according to the path direction information of the drainage pipe network, find each drainage pipe network detection well upstream of the first detection position, and obtain at least one second detection position;

[0051] When the first detection position exists a mixed connection situation, according to the path direction information of the drainage pipe network, the first position of the mixed connection situation is found.

[0052] Specifically, the geographic information system (GIS) map of the drainage pipe network of the current detection area to be detected can be obtained in advance, wherein the GIS map of the drainage pipe network contains the path arrangement information of the drainage pipe network and the slope direction information of the drainage pipe network. According to the slope information contained in the GIS map of the drainage pipe network, the distribution positions of each drainage pipe network detection well contained upstream of the first detection position are determined. When the first detection position exists a mixed connection situation, the distribution positions of each drainage pipe network detection well contained upstream of the first detection position are selected as the preselected second detection positions. The number of the second detection positions is determined according to the actual path arrangement information of the drainage pipe network contained in the GIS map of the drainage pipe network. In a specific case, the number of the second detection positions is at least one.

[0053] S104, obtaining the second detection results of volatile organic compounds of in-situ time-of-flight mass spectrometry of each second detection position;

[0054] In a specific embodiment, when the in-situ time-of-flight mass spectrometry of volatile organic compounds of each second detection position is detected, the second detection results of volatile organic compounds of in-situ time-of-flight mass spectrometry of each second detection position can be obtained in sequence from the first detection position along the downstream to upstream according to the path direction information of the drainage pipe network.

[0055] S105, based on the path direction information of the drainage pipe network, inputting each second detection result into the trained mixed connection judgment model in sequence from downstream to upstream for mixed connection judgment, finding the detection well located at the most upstream among the detection wells with mixed connection situation, and obtaining the mixed connection point of the drainage pipe network.

[0056] Each second detection result obtained is input into the trained mixed connection judgment model for mixed connection judgment. Specifically, according to the path direction information of the drainage pipe network, whether each second detection position exists a mixed connection situation is sequentially investigated and judged from downstream to upstream, until the detection well located at the most upstream with a mixed connection situation is found and is taken as the mixed connection point of the current drainage pipe network.

[0057] After the mixed connection point is obtained, the rain and sewage diversion reconstruction of the current mixed connection point drainage pipe network can be implemented. In the embodiment, the mixed connection judgment model constructed and trained in advance is used to determine the most upstream rain and sewage mixed connection point of the drainage pipe network based on the detection results of volatile organic compounds of the in-situ time-of-flight mass spectrometer at each detection position along the drainage pipe network, so that the mixed connection position can be intelligently and quickly determined.

[0058] In a preferred embodiment, the mixed connection judgment model in the embodiment can also estimate the rain and sewage mixed connection degree of the water sample at the mixed connection position according to the detection results of specific volatile organic compounds, sort and rank according to the estimation results of the rain and sewage mixed connection degree, and determine the priority of reconstruction based on the sorting and ranking.

[0059] The mixed connection judgment model constructed and trained based on the machine learning method is used in the embodiment, and the rain and sewage mixed connection point is determined and traced based on the characteristics of volatile organic compounds in the drainage pipe network, so that the rain and sewage mixed connection degree can be estimated, the speed and intelligent degree of mixed connection point identification and pollution source tracing are improved, and new and high-quality support can be provided for the resilience improvement of urban drainage pipe network.

[0060] Please refer to Figure 2 The second embodiment of the rain and sewage mixed connection detection and tracing method based on the time-of-flight mass spectrometer of the drainage pipe network in the embodiment includes:

[0061] S201, obtain the drainage pipe network geographic information system map in the detection range, and determine the residential area sewage well, industrial area sewage well and non-mixed end rainwater well according to the drainage pipe network geographic information system map, to obtain a plurality of sample detection wells;

[0062] In the embodiment, in order to quickly and intelligently identify the wastewater properties in the inspection well, the mixed connection judgment model constructed based on the machine learning model is pre-trained, and the mixed connection judgment model is called to determine the actual mixed connection state according to the data information of the water sample obtained at each detection position along the drainage pipe network. Therefore, first, the sample data needs to be obtained, the mixed connection judgment model is trained based on the correlation and feature information between the water type, water quality detection information and volatile organic compound detection results of the time-of-flight mass spectrometer of the water sample, and the final mixed connection point is determined based on the trained mixed connection judgment model. Therefore, the training data needs to be collected first in this step.

[0063] Firstly, the Geographic Information System (GIS) map of the drainage network as a sample area is carefully reviewed, and the inspection wells of the sewage pipe network in the residential and industrial areas are selected and marked out. Through field investigation, the end rainwater well without water flow is determined, and the selected water wells are used as sample detection wells. The sample area can be the drainage network area to be currently reconstructed, or a geographical area similar to the drainage network area to be reconstructed in terms of geographical conditions and drainage system.

[0064] S202, in-situ time-of-flight mass spectrometry of volatile organic compounds is performed on the sample detection well to obtain first sample mass spectrometry detection data, and a water sample is collected;

[0065] The selected inspection wells are collected for water samples and in-situ time-of-flight mass spectrometry of volatile organic compounds to obtain first sample mass spectrometry detection data after dry and rainy days, respectively, and the detection results are calibrated according to the source information of the water sample detection data.

[0066] In a preferred embodiment, when using a time-of-flight mass spectrometer for detection, a continuous real-time monitoring method is used, and one detection is completed within 2 seconds. When sampling, first connect the air suction probe with filtering function to the time-of-flight mass spectrometer sampling pump, then insert the probe into the crowbar hole of the inspection well, wait for 30 seconds, record the sampling time, complete the volatile organic compound detection, and then open the well cover to collect the water sample. The gas escaping during the opening of the well cover may cause inaccurate detection. Specifically, the mass-to-charge ratio (m / z, Mass-to-charge ratio) of the time-of-flight mass spectrometry detection ranges from 10 to 400.

[0067] S203, the water sample is divided into first and second types, the first type is directly detected for water quality to obtain water quality parameters, the second type is divided into several parts, respectively cultured at different temperatures, mixed with the third type, and the mixed water sample is detected for volatile organic compounds by time-of-flight mass spectrometry to obtain second mass spectrometry detection data;

[0068] After the water sample is collected, it is divided into two parts, including the first and second types; the first type is directly used for water quality detection to obtain water quality parameters; the second type is divided into several parts, which are respectively cultured at different temperatures for different times, then mixed with the third type of water sample belonging to other types of water in different proportions to obtain mixed water samples, wherein the third type of water sample includes rainwater, chemical sewage, domestic sewage, etc. Then the mixed water sample is detected for water quality, and the volatile organic compounds in the headspace are detected by time-of-flight mass spectrometry to obtain second mass spectrometry detection data.

[0069] The water quality detection content includes: phosphorus content, nitrogen content in the form of free ammonia in the water sample, chemical oxygen demand consumed when reducing substances contained in the water sample are oxidized, and three-dimensional fluorescence spectrum characteristics of the water sample. In a specific embodiment, the three-dimensional fluorescence spectrum characteristics are determined after filtering with a 0.22 μm filter during detection, and the excitation wavelength range is 200-700 nm, and the emission wavelength range is 250-750 nm.

[0070] In a specific embodiment, when the water sample is cultured, the culture temperature can be selected from various temperatures, such as 10°C, 15°C, 20°C, and 25°C; the culture time can be selected from various times, including 2h, 4h, 8h, 12h, 16h, 24h, 30h, 38h, and 48h; so as to simulate the water quality changes that may occur when sewage stays in a pipeline or a water well for different lengths of time at different temperatures in real situations.

[0071] When the obtained water sample is directly subjected to in-situ volatile organic compound detection by time-of-flight mass spectrometry, and the water sample after mixing is subjected to volatile organic compound detection by time-of-flight mass spectrometry, the same water sample is collected multiple times, and the volatile organic compound detection collection time is recorded. The multiple collection results of the same water sample are preprocessed according to the detection collection time; the preprocessing includes average processing and mass spectrum denoising operations.

[0072] Specifically, in a preferred embodiment, the time stamp of the mass spectrum file can be queried by a Python program, and it is determined according to the time stamp which are the multiple collection results of the same water sample, and the multiple collection results are subjected to average processing. Subsequently, the first mass spectrum detection data and the second mass spectrum detection data collected are subjected to mass spectrum denoising.

[0073] The training method of the mixing judgment model described in this embodiment collects VOCs in-situ detection data by time-of-flight mass spectrometry of different weather, different regions, and different types of sewage, and obtains detection data by headspace time-of-flight mass spectrometry VOCs detection under different temperatures, different residence times, and different external water mixing ratios in the laboratory, constructs a rich drainage pipe network VOCs mass spectrum data set, provides comprehensive data samples for model training, and enhances the accuracy of subsequent model identification.

[0074] S204, marking the water sample type label on the preprocessed sample mass spectrum detection data, and selecting features according to different feature selection methods;

[0075] The mass spectrum detection data of the preprocessed water samples are marked with water sample type labels according to their specific types, and the water sample type labels can be determined according to the water quality parameters of each water sample.

[0076] Subsequently, different feature selection methods are called to perform feature selection on the mass spectrum detection data of each sample, that is, to select appropriate mass spectrum peaks as model variables, and the feature selection includes the following methods:

[0077] (1) The candidate features are initially screened through the dynamic correlation degree between the water quality parameters and the volatile organic compound detection data;

[0078] (2) The candidate features are supplemented and verified based on the pre-constructed knowledge base in the field;

[0079] (3) The adaptive algorithm is used to optimize the final feature set.

[0080] The dynamic correlation degree calculation in step (1) includes but is not limited to: correlation coefficient analysis, mutual information calculation, time lag causal inference, etc. Taking the correlation coefficient analysis method as an example, the water quality detection results and the volatile organic compound detection results (i.e. the first mass spectrum detection data and the second mass spectrum detection data) are subjected to correlation analysis, and a plurality of volatile organic compounds with strong correlation between the mass spectrum detection integral and the water quality detection results are selected as the feature variables for machine learning, and the characteristic volatile organic compounds reflecting the water quality type are selected from the literature as supplements, and the total signal integral is also used as a feature.

[0081] In a preferred embodiment, the water quality parameters subjected to correlation analysis with the volatile organic compound mass spectrum signal integral include some water quality parameters for characterizing sewage characteristics, fluorescence index (FI) of three-dimensional fluorescence, biological index (BIX), humification index (HIX), and components of parallel factor analysis. In a specific example, the mass number of the mass spectrum peaks selected as model variables includes but is not limited to: 49.1, 63.1, 35.08, 60.1, 95.2, 77.1, 105.2, 39.0, 43.0, 47.0, 48.0, 53.0, 56.0, 60.0, 73.0, 74.0, 77.0, 92.0, 113.1, 125.1, etc. Due to the small number of mass drifts that cannot be eliminated by the instrument, the peak area of the mass number used in the present application is not limited to the specific numbers above, but is the mass spectrum peak of the substance closest to the above mass number.

[0082] When selecting model variables in the feature selection part in this step, methods such as wrapping, filtering and embedding can be used. For example, taking the correlation coefficient selection method in the filtering method as an example, please refer to Figure 3The correlation between the area of a certain mass-to-charge ratio peak (mass-to-charge ratio m / z = 1) and the chemical oxygen demand (COD) can be analyzed to select the mass spectrum peaks with high correlation with each water quality parameter as the model features. The correlation coefficient selection method is only one specific example, and the feature selection method in the model variable selection part of the present application is not limited to this method. In addition, some volatile organic compounds in sewage in existing literature can also be used as supplementary features.

[0083] S205, using the results of the feature selection and the corresponding water sample type label information, training the initial machine learning model to obtain the trained mixed connection judgment model;

[0084] The features selected in the foregoing step S204 are used, and at the same time, the water sample type label (such as sewage, mixed sewage, and rainwater) when the water sample is collected is used as the training label to train the initial machine learning model constructed using the machine learning algorithm to obtain the trained mixed connection judgment model. The machine learning algorithm used in the initial machine learning model includes but is not limited to random forest, support vector machine, artificial neural network, etc.

[0085] In one specific embodiment, the initial machine learning model uses a support vector machine as an initial rainwater identification algorithm; when training the model, a training set is generated using the results of the feature selection and the corresponding water sample type label information, and a hyperplane of the support vector machine is constructed; the distance of each sample point in the training set to the hyperplane is calculated, and the Lagrange multiplier method is introduced to obtain the hyperplane with the farthest sample to the hyperplane, so that the distance between the nearest point in the sample of different categories to the hyperplane is maximized, thereby realizing the classification of subsequent samples, and updating the hyperparameters of the model; a test set is generated based on the results of the feature selection and the corresponding water sample type label information, and the test set is called to test the model after updating the hyperparameters, and when the test result accuracy meets the test requirements, the trained mixed connection judgment model is obtained.

[0086] As a specific example, for a given training set with an n-dimensional variable matrix The hyperplane of the support vector machine is represented as:

[0087]

[0088] The distance of the sample point to the hyperplane is:

[0089]

[0090] wherein, For the module.

[0091] To find the hyperplane with the maximum distance to the samples, the support vector machine fixes the value of , and finds For easy calculation, the problem can be converted to find Then, the Lagrange multiplier method is introduced to further solve the problem, and the optimal hyperplane is obtained.

[0092] In addition, regarding the step of testing the model after updating the hyperparameters by using the test set, the model can be tested by using the test set to obtain a confusion matrix. For a specific example of a confusion matrix, please refer to Table 1:

[0093] Table 1 Confusion matrix of machine learning identification model test

[0094]

[0095] It can be seen that the model performs excellently on the test set, with an identification accuracy of 96.9%. This indicates that volatile organic compound detection based on time-of-flight mass spectrometry can be used to accurately identify rainwater and sewage mixing, greatly improving the efficiency of drainage pipe network mixing identification, and providing technical support for the healthy supervision of drainage pipe networks.

[0096] Based on the above scheme, the embodiment innovatively uses a time-of-flight mass spectrometer to accurately detect volatile organic compounds in drainage pipe networks, and selects characteristic volatile organic compounds related to water quality factors to construct a machine learning model for judging rainwater and sewage mixing. The model can accurately diagnose rainwater and sewage mixing and can be used in high-water-level drainage pipe networks that are difficult to detect by visual detection methods.

[0097] S206, obtaining a first detection result of volatile organic compounds of the in-situ time-of-flight mass spectrometer at a first detection position along the drainage pipe network;

[0098] After the test result accuracy meets the test requirements and the trained mixing judgment model is obtained, the trained mixing judgment model can be used to judge and trace the actual rainwater and sewage mixing situation along the drainage pipe network. The specific content in this step S206 is basically the same as that in the step S101 of the foregoing embodiment, and therefore will not be described here.

[0099] S207, inputting the first detection result into the trained mixing judgment model to judge the mixing, and determining whether there is mixing at the first detection position;

[0100] S208, if the first detection position exists a mixed connection situation, according to the path direction information of the drainage pipe network, find each drainage pipe network detection well upstream of the first detection position, and obtain at least one second detection position;

[0101] S209, obtain the second detection result of volatile organic compounds of the in-situ time-of-flight mass spectrometer of each second detection position;

[0102] S210, based on the path direction information of the drainage pipe network, input each second detection result into the trained mixed connection judgment model in order from downstream to upstream for mixed connection judgment, find the detection well at the most upstream in each detection well with mixed connection, and obtain the drainage pipe network mixed connection point;

[0103] The specific content in steps S207-S210 in this embodiment is basically the same as that in steps S102-S105 in the foregoing embodiment, and thus is not described here.

[0104] After completing the preliminary data sample collection and model training work, the time-of-flight mass spectrometer instrument can be used to quickly collect in-situ volatile organic compound information without opening the manhole cover. In actual conditions, hundreds of inspection wells can be checked in a day under the condition that the traffic condition permits, greatly improving the mixed connection checking efficiency.

[0105] S211, collect the third detection result of volatile organic compounds of the in-situ time-of-flight mass spectrometer of the detection well upstream of the drainage pipe network mixed connection point, and respectively obtain the volatile organic compound characteristics of domestic sewage around the drainage pipe network mixed connection point region and the volatile organic compound characteristics of industrial wastewater around the drainage pipe network mixed connection point region;

[0106] After detecting the original rainwater and sewage mixed connection point detection well position, this embodiment can also calculate the sewage type and sewage mixed connection ratio according to the specific detection result of the water sample obtained at the mixed connection point position. Specifically, the water sample obtained at the mixed connection point may be a mixed water sample of domestic sewage and rainwater, a mixed water sample of chemical sewage and rainwater, or a mixed water sample containing domestic sewage, chemical sewage and rainwater. The environmental impact effect of sewage is different under different mixed conditions, so it is necessary to judge the specific mixed connection situation of the sewage to determine the priority of subsequent reconstruction.

[0107] Therefore, in this embodiment, after determining the drainage pipe network mixed connection point, the third detection result of volatile organic compounds of the in-situ time-of-flight mass spectrometer of the detection well upstream of the drainage pipe network mixed connection point is collected, and the volatile organic compound characteristics of domestic sewage around the drainage pipe network mixed connection point region and the volatile organic compound characteristics of industrial wastewater around the drainage pipe network mixed connection point region are respectively obtained.

[0108] S212, calling a mixing ratio algorithm, fitting and solving according to the third detection result, the volatile organic compound characteristics of the surrounding domestic sewage of the drainage pipe network mixing point area and the volatile organic compound characteristics of the surrounding industrial wastewater to obtain the sewage type and the sewage mixing ratio in the current mixing point.

[0109] According to the volatile organic compound characteristics of the surrounding domestic sewage of the drainage pipe network mixing point area and the volatile organic compound characteristics of the surrounding industrial wastewater of the drainage pipe network mixing point area, several characteristic volatile organic compounds are selected, the volatile organic compound data of the mixing point is taken as a target function, the characteristic volatile organic compounds of the surrounding domestic sewage and industrial wastewater upstream of the mixing point are taken as variables to solve by least square method, and an optimal fitting equation is obtained, according to which it is judged that what kind of external sewage is mixed into, and the mixed proportion of the contained sewage is inferred. Finally, the fitting coefficients corresponding to the characteristic volatile organic compounds are ranked and rated to determine the priority of subsequent reconstruction.

[0110] Specifically, the several characteristic volatile organic compounds are specified according to the specific circumstances of the surrounding domestic sewage and industrial wastewater, the signal strength of the domestic sewage volatile organic compounds used for least square fitting is calibrated at a chemical oxygen demand of 300 mg / L of the water sample, and the industrial wastewater concentration is accurate at the factory concentration. When ranking and rating, different pollution wastewater mixing ratios are scored: less than or equal to 10% is 1 point, greater than 10% and less than or equal to 20% is 2 points, greater than 20% and less than or equal to 30% is 3 points, greater than 30% and less than or equal to 40% is 4 points, and greater than 40% is 5 points. Finally, different comprehensive weights are given by the local environmental protection department according to the harm degree of different wastewater to the environment, and the scores are weighted and summed to provide priority basis for subsequent reconstruction.

[0111] The present application is based on the process described in the embodiment, specifies a sampling plan according to the drainage pipe network path information of the geographic information system, continuously detects the volatile organic compounds of the drainage pipe network from downstream to upstream, quickly masters the volatile organic compound information of the whole area drainage pipe network, effectively identifies the mixing point, and traces the pollution to the residential area and each factory according to the volatile organic compound characteristics, and forms a deeper understanding of the actual situation of the regional drainage pipe network.

[0112] The scheme in the embodiment of the application is aimed at the characteristic differences of volatile organic compounds of rainwater and sewage in the drainage pipe network, uses a time-of-flight mass spectrometer to accurately detect volatile organic compounds in the drainage pipe network under different weather and different regions, simulates the characteristics of volatile organic compounds under different temperatures, different residence times and different mixing ratios, constructs a comprehensive mass spectrum data set of volatile organic compounds in the drainage system, and trains a mixed connection discrimination model based on characteristic volatile organic compounds as variables of a machine learning model. According to the mixed connection discrimination model obtained by training, the characteristics of volatile organic compounds in the drainage pipe network are identified, so that the judgment and tracing of the rain-sewage mixing point are realized, and the speed and intelligent degree of the identification of the mixing point and the tracing of the pollution source are improved. Finally, the proportion of external water inflow is inferred by least square solution based on the volatile organic compound information of the upstream of the mixing point and the surrounding area, and the mixing point is scored according to the mixing degree and the pollution hazard degree, so as to provide priority basis for subsequent reconstruction.

[0113] Please refer to Figures 4-9 The third embodiment of the rain-sewage mixing detection and tracing method based on the time-of-flight mass spectrometer in the embodiment of the application includes:

[0114] In the embodiment of the application, a specific implementation scenario is taken as an example to illustrate the judgment effect of the rain-sewage mixing detection and tracing method based on the time-of-flight mass spectrometer. The details of the rain-sewage mixing detection and tracing method in the embodiment can be referred to the content in the foregoing second embodiment, and will not be described here.

[0115] In a specific implementation scenario, the rain-sewage mixing detection and tracing of the drainage pipe network is carried out based on the actual situation of an industrial park. As shown in Figure 4 , the left side is the upstream end of the rainwater pipe, and there are three chemical enterprises Q1, Q2 and Q3 along the line of the rainwater main, which discharge production wastewater from the enterprise internally from three directions and collect it into the sewage main pipe parallel to the rainwater main (the sewage main pipe is not drawn in the figure).

[0116] The time-of-flight mass spectrometer is used to detect the sewage collected from the sewage outlets of the three enterprises Q1, Q2 and Q3 and the upstream rainwater, and the time-of-flight mass spectrum as shown in Figures 5-8 is obtained. In order to simulate the rain-sewage mixing situation of the rainwater main, the sewage of the three enterprises is mixed into the upstream rainwater according to different proportions. In a specific example, a specific mixing ratio is shown in Table 2:

[0117] Table 2 Actual wastewater mixing ratio of simulation scenario

[0118]

[0119] The mixed wastewater is also detected by time-of-flight mass spectrometry, and a time-of-flight mass spectrum as shown in Figure 9 is obtained.

[0120] Next, the mass spectrum results obtained by time-of-flight mass spectrometry are directly used for least square method solving, and the mixed degree solving results of the wastewater of different enterprises are obtained as shown in Table 3:

[0121] Table 3 Mixed connection results calculated based on the least square method

[0122]

[0123] For the analysis of the calculation results, the least square method calculation results show high consistency with the true mixing ratio, and accurately identify that Q1 and Q2 are the proportions of the two main wastewater, and show a lower estimate for the proportion of Q3, which indicates that the method in the application has very good judgment effect on the proportion of rainwater and sewage mixing.

[0124] Please refer to Figure 10 , the fourth embodiment of the rainwater and sewage mixing detection and tracing method based on time-of-flight mass spectrometry in the embodiment of the application comprises:

[0125] In the embodiment of the application, a specific implementation scenario is taken as an example to illustrate the specific application scheme of the rainwater and sewage mixing detection and tracing method based on time-of-flight mass spectrometry described in the application. The details of the rainwater and sewage mixing detection and tracing method described in the embodiment can be referred to the contents in the foregoing second embodiment, and will not be described here.

[0126] Step one: according to the municipal drainage system GIS schematic diagram as shown in Figure 10 , a time-of-flight mass spectrometry test scheme along the line is formulated for a municipal drainage network, and in-situ time-of-flight mass spectrometry detection is carried out;

[0127] Step two: the detection results are imported into a machine learning model for classification, and the model identifies sewage components in the rainwater inspection well B and multiple rainwater inspection wells downstream of the rainwater inspection well B, and discriminates them as sewage wells;

[0128] Step three: it is found through field geophysical prospecting that a community sewage outlet pipe is misconnected to the B inspection well, causing sewage to flow into the rainwater pipe. The time-of-flight mass spectrometry data of the rainwater well A upstream of the inspection well B is recorded as , the time-of-flight mass spectrometry data of the standard sewage concentration (COD=300mg / L) of the area is recorded as , and the least square method calculation is carried out to obtain the result as This shows that there may be about 26% of sewage mixed into the B inspection well, of course, the intercept of-0.04 also provides a certain elasticity space for estimation, and the result is only as a basis for sorting the mixing degree of the whole area.

[0129] To sum up, the present application is aimed at the characteristic differences of volatile organic compounds of rainwater and sewage in the drainage pipe network, and the volatile organic compounds in the drainage pipe network under different weather and different regions are accurately detected by using a time-of-flight mass spectrometer, the characteristics of volatile organic compounds under different temperatures, different residence times and different mixing ratios are simulated, a comprehensive mass spectrometry data set of volatile organic compounds in the drainage system is constructed, and the mixing discrimination model is obtained based on the characteristic volatile organic compounds as variables of the machine learning model. Finally, the inflow proportion of external water is inferred by least square solution of the volatile organic compound information upstream of the mixing point and the life industrial volatile organic compound information of the surrounding area, and the mixing point is scored according to the mixing degree and pollution hazard degree, so as to provide priority basis for subsequent reconstruction.

[0130] The above describes the drainage pipe network rain and sewage mixing detection and tracing method based on time-of-flight mass spectrometry in the embodiment of the present application, and the drainage pipe network rain and sewage mixing detection and tracing system based on time-of-flight mass spectrometry in the embodiment of the present application is described below, please refer to Figure 11 An embodiment of the drainage pipe network rain and sewage mixing detection and tracing system based on time-of-flight mass spectrometry in the embodiment of the present application includes:

[0131] The data acquisition module 1101 is configured to acquire a first detection result of volatile organic compounds of an in-situ time-of-flight mass spectrometer at a first detection position along the drainage pipe network.

[0132] The mixing detection module 1102 is configured to input the first detection result into the trained mixing judgment model to determine whether the first detection position has mixing.

[0133] The mixing tracing module 1103 is configured to, if the first detection position has mixing, find each drainage pipe network detection well upstream of the first detection position according to path direction information of the drainage pipe network to obtain at least one second detection position, acquire a second detection result of volatile organic compounds of an in-situ time-of-flight mass spectrometer at each second detection position, input each second detection result into the trained mixing judgment model in order from downstream to upstream based on the path direction information of the drainage pipe network, find the detection well at the most upstream in each detection well with mixing, and obtain a mixing point of the drainage pipe network.

[0134] The embodiment of the present application uses a mixed connection judgment model constructed and trained based on a machine learning method, identifies based on volatile organic matter characteristics in a drainage pipe network, thereby realizing judgment and tracing of a rain and sewage mixed connection point, and can estimate the degree of rain and sewage mixed connection, improves the speed and intelligent degree of mixed connection point identification and pollution source tracing, and can provide new and high-quality support for the resilience improvement of the urban drainage pipe network.

[0135] Please continue to refer to Figure 12 In another embodiment of the present application, the time-of-flight mass spectrometry-based rain and sewage mixed connection detection and tracing system for a drainage pipe network further comprises a proportion calculation module 1104, specifically configured to:

[0136] Collect a third detection result of volatile organic matter of an in-situ time-of-flight mass spectrometer of a detection well upstream of the mixed connection point of the drainage pipe network, and respectively acquire volatile organic matter characteristics of domestic sewage around the mixed connection point area of the drainage pipe network and volatile organic matter characteristics of industrial wastewater around the mixed connection point area of the drainage pipe network;

[0137] Call a mixed connection proportion algorithm, and perform fitting and solving according to the third detection result, the volatile organic matter characteristics of domestic sewage around the mixed connection point area of the drainage pipe network, and the volatile organic matter characteristics of industrial wastewater around the mixed connection point area, to obtain the type of sewage in the current mixed connection point and the sewage mixed connection proportion.

[0138] In another embodiment of the present application, the time-of-flight mass spectrometry-based rain and sewage mixed connection detection and tracing system for a drainage pipe network further comprises a model training module 1105, and the model training module 1105 specifically comprises:

[0139] A sample acquisition unit 11051 configured to acquire water body samples under multiple different mixed connection proportions, and perform water quality detection and volatile organic matter detection of the time-of-flight mass spectrometer on the water body samples to obtain multiple sample mass spectrum detection data;

[0140] A feature selection unit 11052 configured to mark a water sample type label on each of the preprocessed sample mass spectrum detection data, and perform feature selection according to different feature selection methods;

[0141] A model training unit 11053 configured to use the result of feature selection and corresponding water sample type label information to train an initial machine learning model to obtain a trained mixed connection judgment model.

[0142] In another embodiment of the present application, the sample mass spectrum detection data comprises first sample mass spectrum detection data and second sample mass spectrum detection data;

[0143] The sample acquisition unit 11051 is specifically further configured to:

[0144] acquire a sewerage network geographic information system map in a detection range, and determine a residential area sewage well, an industrial area sewage well, and a non-mixed end rainwater well according to the sewerage network geographic information system map, to obtain a plurality of sample detection wells;

[0145] perform in-situ time-of-flight mass spectrometry volatile organic compound detection on the sample detection wells to obtain first sample mass spectrometry detection data, and collect water body samples;

[0146] divide the water body samples into first-type water samples and second-type water samples, directly detect water quality of the first-type water samples to obtain water quality parameters, divide the second-type water samples into several portions, mix the portions with third-type water samples after culturing at different temperatures, and perform time-of-flight mass spectrometry volatile organic compound detection on the mixed water samples to obtain second mass spectrometry detection data.

[0147] In another embodiment of the present application, the feature selection unit 11052 is specifically further configured to:

[0148] associate water quality parameters of the same sample with the sample mass spectrometry detection data, and preliminarily screen candidate features according to a dynamic correlation degree;

[0149] supplementally verify the preliminarily screened candidate features based on a pre-constructed water quality field knowledge base;

[0150] optimize the supplementally verified preliminarily screened candidate features by using an adaptive algorithm to obtain a final feature set, and complete selection of the features.

[0151] In another embodiment of the present application, the initial machine learning model uses a support vector machine as an initial rain and sewage identification algorithm; and the model training unit 11053 is specifically configured to:

[0152] generate a training set by using results of the feature selection and corresponding water sample type label information, and construct a hyperplane of the support vector machine;

[0153] calculate distances of sample points in the training set to the hyperplane, introduce a Lagrange multiplier method to obtain a hyperplane with the farthest sample to the hyperplane, maximize distances between points closest to the hyperplane in different categories and the hyperplane, and update hyperparameters of the model;

[0154] generate a test set by using results of the feature selection and corresponding water sample type label information, and test the model after updating the hyperparameters by using the test set, to obtain a trained mixed connection judgment model when an accuracy rate of a test result meets a test requirement.

[0155] The solution in the embodiment of the present invention targets the differences in volatile organic compound (VOC) characteristics between rainwater and sewage in the drainage network. It utilizes a time-of-flight mass spectrometer to accurately detect VOCs in the drainage network under different weather conditions and in different regions. It simulates the VOC characteristics of different temperatures, residence times, and mixing ratios, constructs a comprehensive VOC spectral dataset for the drainage system, and trains a machine learning model based on the characteristic VOCs as variables to generate a mixing discrimination model. The trained mixing discrimination model identifies VOC characteristics in the drainage network, thereby enabling the identification and tracing of rainwater and sewage mixing points, improving the speed and intelligence of mixing point identification and pollution source tracing. Finally, a least squares solution is performed using VOC information upstream of the mixing point and VOC information from domestic and industrial sources in the surrounding area to infer the proportion of external water inflow. Mixing points are then scored based on the degree of mixing and the degree of pollution hazard, providing a priority basis for subsequent renovations.

[0156] Based on the same inventive concept, an embodiment of this specification also provides an electronic device for detecting and tracing the mixing of rainwater and sewage in a drainage network based on time-of-flight mass spectrometry. The following is a detailed description of the electronic device for detecting and tracing the mixing of rainwater and sewage in a drainage network based on time-of-flight mass spectrometry in an embodiment of the present invention from the perspective of hardware processing.

[0157] Figure 13 This is a schematic diagram of the structure of an electronic device provided in the embodiment of this specification. Figure 13 The electronic device 1300 according to this embodiment of the present invention will be described. Figure 13 The electronic device 1300 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0158] like Figure 13 As shown, electronic device 1300 is implemented as a general-purpose computing device. Components of electronic device 1300 may include, but are not limited to, at least one processing unit 1310, at least one storage unit 1320, a bus 1330 connecting various system components (including storage unit 1320 and processing unit 1310), and a display unit 1340.

[0159] The storage unit stores program codes, which can be executed by the processing unit 1310, so that the processing unit 1310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 1310 can perform the following steps: Figure 1 or Figure 2 Steps shown.

[0160] The storage unit 1320 can include a readable medium in the form of volatile storage such as random access memory (RAM) 13201 and / or cache memory 13202, and also can include non-volatile storage such as read only memory (ROM) 13203.

[0161] The storage unit 1320 also can include a program / utility 13204 having a set (at least one) of program modules 13205, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof, can include implementation of a network environment.

[0162] The bus 1330 can represent one or more of several types of bus structures, including a storage bus or bus controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus structures, and the like.

[0163] The electronic device 1300 also can communicate with one or more external devices 100 such as a keyboard or a pointing device, a Bluetooth device, etc., and also can communicate with one or more devices that enable a user to interact with the electronic device 1300 and / or any devices (e.g., a router, a modem, etc.) that enable the electronic device 1300 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 1350. Still yet, the electronic device 1300 can communicate with one or more networks such as a local area network (LAN), a general wide area network (WAN), and / or a public network such as the Internet, via a network adapter 1360. The network adapter 1360 can be any of a plurality of different types of adapters to enable the electronic device 1300 to communicate with such networks and is coupled with the other components of the electronic device 1300 via the bus 1330. It should be appreciated that while not shown, other hardware and / or software components could be used in conjunction with the electronic device 1300. These include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc. Figure 13

[0164] In addition, the present application also provides a computer program product, comprising computer programs / instructions, which, when executed by a processor, implement the method for detecting and tracing rainwater and sewage mixed connection of a drainage network based on time-of-flight mass spectrometry as described in any of the above embodiments.

[0165] ​Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described in the present application can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a computer readable storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to perform the above-mentioned method according to the present application. When the computer program is executed by a data processing device, the computer readable medium enables the computer to implement the above-mentioned method of the present application, that is, the method shown in Figure 1 or Figure 2 the steps.

[0166] Figure 14 A schematic diagram of a computer readable medium provided for the embodiments of the present application.

[0167] The computer program for implementing Figure 1 or Figure 2 the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable 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.

[0168] The computer readable storage medium can include a data signal propagating in a baseband or as a carrier wave in a propagated data signal, in which the readable program code is carried. Such a propagated data signal can take on many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium can also be any readable medium that is not a readable storage medium, which can send, propagate or transmit programs for use by or in connection with an instruction execution system, apparatus or device. The program code contained on the readable storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0169] The program code may be implemented in any of various ways, including procedure-based (e.g., C), object-oriented (e.g., Java), and / or design-based (e.g., Veloprint) ways. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device (e.g., through the Internet using an Internet Service Provider).

[0170] In light of the above, the present application can be implemented in hardware, or software on one or more processors, or a combination of both. Those skilled in the art will appreciate that the various embodiments can be implemented in their entirety, or any part, in one or more general purpose data processing devices, special purpose data processing devices, or any other device. The present application can also be implemented as a program of instructions for implementing any part of the above-described methods on a data processing device or apparatus (e.g., a computer program and a computer program product). Such a program of instructions can be stored on a computer readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0171] The above-described embodiments are merely intended to further describe the purpose, technical solutions and beneficial effects of the present application, and should be understood that the present application is not inherently related to any specific computer, virtual device or electronic device, and various general-purpose devices can also implement the present application. The above-described embodiments are merely specific embodiments of the present application, and are not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

[0172] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0173] If the technical scheme of the application involves personal information, the product applying the technical scheme of the application has been explicitly informed of the personal information processing rules before processing the personal information and has obtained the personal independent consent. If the technical scheme of the application involves sensitive personal information, the product applying the technical scheme of the application has obtained the personal independent consent before processing the sensitive personal information and at the same time meets the requirement of "explicit consent".

[0174] The above only describes the embodiments of the application and is not used to limit the application. The application can have various changes and modifications for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application shall be included in the scope of claims of the application.

Claims

1. A method for detecting and tracing the mixing of rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry, characterized in that: include: Obtaining a first detection result of volatile organic compounds by in-situ time-of-flight mass spectrometry at a first detection location along the drainage network; Inputting the first detection result into the trained hybrid connection judgment model to perform hybrid connection judgment to determine whether there is hybrid connection at the first detection position; If there is a mixed connection at the first detection position, then search for each drainage network detection well upstream of the first detection position according to the path direction information of the drainage network to obtain at least one second detection position; Obtaining a second detection result of volatile organic compounds by in-situ time-of-flight mass spectrometry at each of the second detection positions; Based on the path direction information of the drainage network, each of the second detection results is input into the trained mixed connection judgment model in order from downstream to upstream for mixed connection judgment. Among the detection wells where mixed connection exists, the detection well at the upstreammost end is searched to obtain the mixed connection point of the drainage network.

2. The method for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry according to claim 1 is characterized in that: After obtaining the drainage network mixing point, the method further includes: Collecting a third detection result of volatile organic compounds by in-situ time-of-flight mass spectrometry from a detection well upstream of the drainage network mixing point, and respectively obtaining volatile organic compound characteristics of domestic sewage and industrial wastewater in the vicinity of the drainage network mixing point; The mixing ratio algorithm is called to perform fitting and solving based on the third detection result, the volatile organic compound characteristics of domestic sewage around the mixing point area of ​​the drainage network, and the volatile organic compound characteristics of the surrounding industrial wastewater to obtain the sewage type and sewage mixing ratio in the current mixing point.

3. The method for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry according to claim 1 or 2, characterized in that: Before obtaining a first detection result of volatile organic compounds by in-situ time-of-flight mass spectrometry at a first detection position along the drainage network, the method further includes: Acquiring water samples under multiple mixing ratios, and performing water quality testing and volatile organic compound testing using time-of-flight mass spectrometry on the water samples to obtain multiple sample mass spectrometry test data; The pre-processed mass spectrometry data of each sample are labeled with a water sample type label, and feature selection is performed according to different feature selection methods; The constructed initial machine learning model is trained using the result of feature selection and the corresponding water sample type label information to obtain the trained hybrid judgment model.

4. The method for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry according to claim 3 is characterized in that: The sample mass spectrum detection data includes first sample mass spectrum detection data and second sample mass spectrum detection data; The method of obtaining water samples under multiple mixing ratios and performing water quality detection and volatile organic compound detection by time-of-flight mass spectrometry on the water samples to obtain multiple sample mass spectrometry detection data includes: Obtain a geographic information system map of the drainage network within the scope of the inspection, and determine the sewage wells in the residential area, the sewage wells in the industrial area, and the terminal rainwater wells without mixed connections based on the geographic information system map of the drainage network to obtain multiple sample inspection wells; Performing in-situ time-of-flight mass spectrometry detection of volatile organic compounds on the sample detection well to obtain first sample mass spectrometry detection data, and collecting a water sample; The water samples are divided into a first type of water sample and a second type of water sample. The water quality of the first type of water sample is directly tested to obtain water quality parameters. The second type of water sample is divided into several parts, and the parts are cultured at different temperatures and then mixed with the third type of water sample. The mixed water samples are then subjected to time-of-flight mass spectrometry for volatile organic compound detection to obtain second mass spectrometry detection data.

5. The method for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry according to claim 4 is characterized in that: The feature selection according to different feature selection methods includes: Correlate the water quality parameters of the same sample with the sample mass spectrometry data, and preliminarily screen candidate features based on the dynamic correlation degree; Supplementary verification of the candidate features of the initial screening is performed based on a pre-built water quality knowledge base; An adaptive algorithm is used to optimize the initial screening candidate features after supplementary verification to obtain the final feature set and complete the feature selection.

6. The method for detecting and tracing mixed rainwater and sewage in drainage pipe networks based on time-of-flight mass spectrometry according to claim 3 is characterized in that: The initial machine learning model uses a support vector machine as an initial rain and pollution recognition algorithm; The result after feature selection and the corresponding water sample type label information are used to train the constructed initial machine learning model to obtain the trained hybrid judgment model including: Use the feature selection results and the corresponding water sample type label information to generate a training set and construct the hyperplane of the support vector machine; Calculate the distance between each sample point in the training set and the hyperplane, introduce the Lagrange multiplier method to solve the hyperplane with the farthest distance from the sample to the hyperplane, maximize the distance between the points closest to the hyperplane in samples of different categories, and update the hyperparameters of the model; A test set is generated based on the result of the feature selection and the corresponding water sample type label information, and the test set is called to test the model after the hyperparameters are updated. When the accuracy of the test result meets the test requirements, the trained hybrid judgment model is obtained.

7. A drainage network rainwater and sewage mixing detection and tracing system based on time-of-flight mass spectrometry, characterized by: include: a data acquisition module, configured to acquire a first detection result of volatile organic compounds by in-situ time-of-flight mass spectrometry at a first detection position along the drainage network; A mixed connection detection module is used to input the first detection result into the trained mixed connection judgment model to perform mixed connection judgment and determine whether there is a mixed connection at the first detection position; The hybrid connection tracing module is used to find the drainage network detection wells upstream of the first detection position according to the path direction information of the drainage network if there is a hybrid connection at the first detection position, and obtain at least one second detection position; obtain the second detection result of volatile organic compounds of the in-situ time-of-flight mass spectrometry at each second detection position; based on the path direction information of the drainage network, input each second detection result into the trained hybrid connection judgment model in order from downstream to upstream to perform hybrid connection judgment, and find the detection well at the most upstream among the detection wells where there is a hybrid connection to obtain the drainage network hybrid connection point.

8. A drainage network rainwater and sewage mixing detection and tracing device based on time-of-flight mass spectrometry, characterized by: The drainage network rainwater and sewage mixing detection and tracing device based on time-of-flight mass spectrometry includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory so that the drainage network rainwater and sewage mixing detection and tracing device based on time-of-flight mass spectrometry performs the steps of the drainage network rainwater and sewage mixing detection and tracing method based on time-of-flight mass spectrometry as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the program / instruction is executed by the processor, the steps of the method for detecting and tracing the mixing of rainwater and sewage in a drainage network based on time-of-flight mass spectrometry are implemented as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for detecting and tracing the mixing of rainwater and sewage in a drainage network based on time-of-flight mass spectrometry as described in any one of claims 1 to 6 are implemented.

Images