A method and system for rapid detection of pollutants

Abstract

The present invention relates to a method and system for rapid detection of pollutants, the method comprising: arranging detection points in a pollution prevention and control area to form a detection point set, the detection points are provided with a pollutant detection device capable of detecting the type of pollutants and their concentrations; determining the spatiotemporal range covered by each detection point and repeating the step until all detection points are processed; if the spatiotemporal range of one or more detection points can cover the entire spatiotemporal range, the set of one or more detection points is used as a rapid detection point set, and the detection points in the rapid detection point set are used for rapid detection. The present invention comprehensively considers the type of pollutants, reduces the number of detection points that need to be detected in real time, and achieves the effect of rapid detection, thereby greatly improving the detection efficiency, and is suitable for complex groundwater pollution monitoring in a wide area.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart cities, and in particular relates to a method and system for rapid detection of pollutants. Background Art

[0002] Groundwater detection is an important part of urban health; groundwater pollution detection refers to the qualitative or quantitative detection of harmful substances that exist or may exist in groundwater to evaluate the degree of groundwater pollution and risk. Groundwater pollution detection is the basis for groundwater pollution prevention and remediation, and is also an important means to evaluate the quality and function of groundwater environment. In order to effectively protect and manage groundwater resources, it is necessary to conduct timely, accurate and comprehensive detection of the dynamic changes of groundwater, grasp the changing laws of groundwater recharge, runoff, discharge, water level, water volume, water quality and other elements, and provide a scientific basis for groundwater resource evaluation, scientific management and environmental problem prevention and control. Groundwater pollution detection equipment mainly includes detection wells, sensors, telemetry terminals and data platforms. The selection of detection equipment should be based on comprehensive consideration of factors such as detection purpose, detection object, detection frequency, detection accuracy, detection cost, etc., and select equipment suitable for groundwater pollution characteristics and detection needs.

[0003] Since groundwater pollution changes in real time, and due to the different burial depths of groundwater, the complex structure of aquifers, and the difficulty in mastering flow patterns, groundwater pollution detection has high technical difficulty and cost. In order to obtain effective reference and achieve effective monitoring, it is necessary to conduct simple and continuous detection of major pollutants in groundwater. In addition, there are various detection methods, and different detection points have different detection methods. Common detection methods include inductively coupled plasma mass spectrometry, which is suitable for the determination of 16 heavy metal elements in groundwater, including cadmium, lead, arsenic, chromium, copper, zinc, nickel, manganese, cobalt, selenium, vanadium, antimony, thallium, molybdenum, beryllium, tin, etc. It has high detection accuracy and a wide detection range, but the detection time is long, the cost is high, and the equipment is complex. There is also chromatography detection technology, which is a commonly used detection technology. It mainly uses gas chromatography electron capture detector to detect halogen organic pollutants in groundwater. Through n-hexane extraction optimization, nine organic chlorine components in groundwater can be detected. For example, gas chromatography-mass spectrometry technology combines the advantages of gas chromatography and mass spectrometry, uses gas chromatography to prepare samples, and uses mass spectrometry for online detection. It can detect multiple pollutants at the same time, has high detection accuracy and a wide detection range, but the detection equipment used is complex and the operation is cumbersome. In addition, there are optical methods, electrochemical methods, biosensor methods, etc., which will not be described in detail here. In summary, there are various detection methods, each with its own advantages and disadvantages, but the most important thing is that the detection overhead of the detection equipment is very large, so the detection efficiency is not high and the detection speed is low.

[0004] With the continuous advancement of artificial intelligence, big data and other technologies, the rapid detection method of groundwater pollutants will pay more attention to real-time detection and intelligence; it is imperative to combine the Internet of Things and big data technology to achieve remote monitoring and intelligent early warning, and improve detection efficiency and accuracy. Based on the above problems, the present invention combines big data technology, discovers the spatiotemporal correlation between detection points through big data and spatiotemporal correlation, comprehensively considers the detection capabilities of different detection points for pollutant types, and reduces the number of detection points that need to be detected in real time, so as to achieve the effect of rapid detection. Summary of the invention

[0005] In order to solve the above problems in the prior art, the present invention proposes a method and system for rapid detection of pollutants, the method comprising:

[0006] Step S1: Deploy detection points in the pollution prevention and control area To form a set of detection points , the detection point is equipped with a detection device capable of detecting pollutants and obtaining detection data; historical detection data are collected and divided into T segments, and for the detection data within each segment time t, its characteristic value is used as the detection data of the segment t; wherein: ;

[0007] Step S2: Determine each detection point The time and space range covered; repeat this step until all detection points All processing has been completed; the specific steps include the following:

[0008] Step S21: Setting the detection point The current space-time range The initial value is ;in: is the time range, is the set of all detection points, which constitutes the complete spatial range;

[0009] Step S22: Obtain an unprocessed detection point and its current time and space range; use formula (1) (2) to calculate different detection points The spatiotemporal correlation coefficient of the detection data ;in: The time Time detection point Detection data at is the neighbor weight; is the set of detection points Number of detection points; ; Is to seek The number of elements in ;

[0010] ; ;

[0011] Step S23: If , then the current space-time range As the space-time range of the detection point p , go to step S3; otherwise, perform time-space reduction in three directions; the first direction The current time range Time in Set as the time point to be reduced, and use formula (5) to calculate the first temporary coefficient , the second direction Is the time point Set as the time point to be reduced, and use formula (6) to calculate the second temporary coefficient ; Third party The current spatial range middle The smallest value Set as the spatial point to be reduced, and use formula (7) to calculate the third temporary coefficient ;in: , ⊆ ; is the first correlation threshold; repeat steps S22 and S23 until all detection points Until all processing is completed;

[0012] ;

[0013] ;

[0014] (7);

[0015] Will The corresponding direction is used as the time-space reduction direction, and the time point to be reduced or the space point to be reduced corresponding to the time-space reduction direction is deleted from the current time-space range to update the current time-space range; return to step S22;

[0016] Step S3: If the spatiotemporal range of one or more detection points can cover the entire spatiotemporal range, the set of one or more detection points is used as a fast detection point set, and the detection points in the fast detection point set are used for fast detection; specifically: if one or more detection points satisfy the following formula (10), the one or more detection points are used as a fast detection point set. As a collection of rapid detection points ;Will The minimum rapid detection point set is used as the determined rapid detection point set, and the detection points in the determined rapid detection point set are used for rapid detection; wherein: ;

[0017] .

[0018] Furthermore, the historical detection data is big data information.

[0019] Furthermore, the characteristic value is an average value, a typical value, a maximum value and / or a minimum value.

[0020] Furthermore, the detection point is provided with a pollutant detection device capable of detecting K types of pollutants, where K is a preset value.

[0021] Furthermore, the detection point is used for online rapid analysis of perfluorinated compounds, pesticides, and antibiotics in agricultural irrigation areas and screening and identification of non-targeted organic matter.

[0022] Furthermore, the detection device is a high-resolution mass spectrometer.

[0023] A pollutant rapid detection system is used to implement the pollutant rapid detection method.

[0024] A pollutant rapid detection device, wherein the pollutant rapid detection control device is used to implement the pollutant rapid detection method.

[0025] A pollutant rapid detection module, wherein the pollutant rapid detection control module is used to implement the pollutant rapid detection method.

[0026] A pollutant rapid detection server, wherein the pollutant rapid detection module is used to implement the pollutant rapid detection method.

[0027] The beneficial effects of the present invention include:

[0028] (1) Combining big data technology, the spatiotemporal correlation between detection points is discovered through big data and spatiotemporal correlation, and is quantified using the spatiotemporal correlation coefficient. The detection capabilities of different detection points for pollutant types are comprehensively considered, and the spatiotemporal coverage of each detection point is dynamically determined through repeated iterations. The number of detection points that need to be detected in real time is reduced to achieve the effect of rapid detection, thereby greatly improving the detection efficiency. Specifically: a spatiotemporal range and a set of associated spatiotemporal ranges are proposed, and the spatiotemporal correlation of detection points is described from a coarse and fine granularity based on big data, avoiding the analysis of complex detection point attribute information and improving the efficiency of rapid detection.

[0029] (2) The rapid detection point set is analyzed and quantitatively scored from the two dimensions of switching stability and rapid detection overhead. By setting the rapid detection point set sequence, the redundancy and robustness of rapid detection are improved. When detection anomalies or detection capacity problems occur, switching between rapid detection point sets can be done at any time according to needs.

[0030] (3) It has strong compatibility with the detection type dimension. By comprehensively considering the detection capabilities of different detection points for pollutant types, it can achieve the effect of rapid detection from the perspective of practical operation, the cost capacity of the detection equipment, and the full coverage of the detection type and the detection space coverage capability. By reducing the number of detection points required for real-time detection and the detection cost, the effect of rapid detection can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0032] Figure 1 This is a schematic diagram of the rapid pollutant detection method provided by the present invention. DETAILED DESCRIPTION

[0033] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0034] The present invention provides a method and system for rapid detection of pollutants. Figure 1 As shown, the method comprises the following steps:

[0035] Step S1: Deploy detection points in the pollution prevention and control area To form a set of detection points , the detection point is equipped with a detection device capable of detecting pollutants and obtaining detection data; historical detection data are collected and divided into T segments, and for the detection data within each segment time t, its characteristic value is used as the detection data of the segment t; wherein: ;

[0036] Preferably: the historical detection data is big data information;

[0037] Preferably: the characteristic value is one of an average value, a typical value, a maximum value, a minimum value, etc.;

[0038] Preferably: the detection point is provided with a pollutant detection device capable of detecting K types of pollutants; each detection point is capable of detecting one or more types of pollutants; and has differentiated detection capabilities;

[0039] Preferably: the detection point is used for online rapid analysis of new pollutants such as perfluorinated compounds, pesticides, antibiotics, etc. in agricultural irrigation areas and screening and identification of non-targeted organic matter, which is applicable to the complex fields of environmental science, analytical chemistry and water quality detection; in the detection process, solid phase extraction, online solid phase extraction, liquid chromatography-tandem mass spectrometry, and / or phase chromatography-mass spectrometry technology are used to perform differential analysis on small molecule compounds such as perfluorinated compounds, pesticides and antibiotics, or volatile and semi-volatile organic pollutants, and automatically extract and enrich target compounds such as perfluorinated compounds, pesticides, antibiotics, etc. from complex detection samples; preferably: a high-resolution mass spectrometer is used at the detection point to construct a screening and identification method for non-targeted organic matter in groundwater in agricultural irrigation areas, which can detect pollutants in groundwater in agricultural irrigation areas and their pollutant concentration data; further, the high-resolution mass spectrometer includes an Orbitrap mass spectrometer and a Fourier transform ion cyclotron resonance mass spectrometer;

[0040] Preferably, the collecting of historical detection data specifically includes: collecting detection data of each detection point in the past N years; for example, N=1-5;

[0041] Preferably: the detection points are arranged according to certain arrangement rules; for example: the detection points are arranged according to groundwater flow direction, geographical location, temperature, arrangement difficulty, arrangement interval, and expert experience;

[0042] Preferably: the number of detection points arranged is related to the size of the pollution prevention and control area and its geographical location;

[0043] Preferably: preprocessing the historical detection data, the preprocessing includes deleting abnormal nodes, data alignment, normalization, cycle folding, etc.;

[0044] Preferably, each segment time is a preset time interval, such as one day, one month, one quarter, etc.;

[0045] Step S2: Determine each detection point The covered space-time range (or associated space-time range set); repeat this step until all detection points All processing has been completed; the specific steps include the following:

[0046] Step S21: Setting the detection point The initial value of the current spatiotemporal range (or associated spatiotemporal range set) is (or{ ); that is, to determine from the full time and full space range; among which: is the time range, It is the complete spatial range formed by all detection points;

[0047] Step S22: Obtain an unprocessed detection point Its current space-time range ; Use formula (1) (2) to calculate different detection points The spatiotemporal correlation coefficient of the detection data ;in: The time Time detection point Detection data at is the adjacent weight, which is the preset value; is the set of detection points Number of detection points; ; It means to seek The number of elements in; through the improved Moran index, with each detection point as the center, a description of each detection point in the time and space dimensions is carried out at the same time within the time and space range; this description is carried out based on each detection point; ;

[0048] ;

[0049] Preferred: Setting ;in: It is the detection point Distance between

[0050] Preferred: When the detection point When they are directly adjacent, , when the two are not adjacent, set ; The term "non-adjacent" means that there is no detection point between the two detection points that is more adjacent to the two detection points; the term "more adjacent" is described by a closer distance or a better detection capability;

[0051] Preferred: Normalize the spatiotemporal correlation coefficients so that they are distributed In the data space, when the correlation coefficient is close to 1, it indicates strong positive autocorrelation, that is, similar values ​​tend to cluster in time and space; when the correlation coefficient is close to -1, it indicates strong negative correlation, that is, similar values ​​tend to disperse in time and space; when the correlation coefficient is close to 0, it indicates random distribution in time and space, with no obvious correlation;

[0052] When alternative mode 1 of step S23 is selected, correspondingly, alternatively, step S22 is specifically as follows: for each detection point , the continuous time range and the associated spatial range are called detection points The associated space-time range; the associated space-time range set is represented as { { ,in: is the associated time and space range number; for each detection point , each current associated time and space range needs to be processed separately until it is determined; for each associated time and space range , respectively calculate the temporal and spatial correlation coefficients ;in: ; is the number of time ranges in the set, that is, the number of continuous time ranges contained in the final associated time range set; at this time, the reduction of the time range can also be discontinuous, and there is no need to perform periodic folding of historical detection data; it is not difficult to see It can be regarded as a whole. Similarly, formula (3) (4) is used to calculate ; ;

[0053] ;

[0054] Step S23: If , then the current space-time range As the space-time range of the detection point p (Enter step S3); otherwise, perform time-space reduction in three directions; the first direction The current time range Time in Set as the time point to be reduced, and use formula (5) to calculate the first temporary coefficient , the second direction Is the time point Set as the time point to be reduced, and use formula (6) to calculate the second temporary coefficient ; Third party The current spatial range middle The smallest value Set as the spatial point to be reduced, and use formula (7) to calculate the third temporary coefficient ;in: , ; is the first correlation threshold; repeat steps S22 and S23 until all detection points Until all processing is completed; it can be understood that the time range and space range in the associated space-time range are both sets; at this time, the time range is continuous but the space range is discontinuous;

[0055] ;

[0056] ;

[0057] (7);

[0058] Will The corresponding direction is used as the time-space reduction direction, and the time point to be reduced or the space point to be reduced corresponding to the time-space reduction direction is deleted from the current time-space range to update the current time-space range; return to step S22; it is not difficult to see that the deletion for direction 1 is to Change to ; The deletion for direction 2 is to Change to ; The deletion for direction 3 is to Change to ;

[0059] Here, the time-space range is expressed in the form of (time range. space range); then the associated time range and space range constitute the time-space range; here, the time range is a continuous time segment sequence, the space range is a set of multiple detection points, and the space range is a set of detection points;

[0060] Preferably: if the spatiotemporal range of the detection point p is empty or the spatiotemporal range size is less than the range size threshold, indicating that the detection point p cannot be used as a representative detection point, then skip the detection point and continue processing the next detection point; wherein: the size of the spatiotemporal range is equal to ; The range size threshold is a preset value; Of course, the cutoff condition for stopping the processing of the detection point p can also be the number of reductions, and the computational complexity can be reduced by reducing the number of reductions;

[0061] At this time, the spatial range and the time range can be tightly coupled or loosely coupled. Obviously, the detection points in the detection point set are not necessarily adjacent. When the physical range makes some detection point areas present a certain similarity, they can be represented by a representative detection point, which can greatly improve the detection speed.

[0062] The step S23 replaces the mode 1 by reducing the time and space range at the same time. When the replacement mode 1 is adopted, the time range can also be discontinuous. It can be seen that the time range and the space range in the associated time and space range are both sets. The step S23 specifically includes the following steps:

[0063] Step S231: for each associated spatiotemporal range in the associated spatiotemporal range set ,like , taking the associated spatiotemporal range set as the detection point The associated space-time range set (enter step S3); otherwise, for each matching The associated space-time range is reduced in time and space; for each associated space-time range to be reduced , find a space-time point that satisfies equations (8) and (9) , and take the space-time point as the space-time point to be reduced; if there is a space-time point to be reduced, proceed to the next step, otherwise, proceed to step S233; repeat steps S231 to S233 until all associated space-time ranges for the detection point p meet , or its associated space-time range set is empty; ;

[0064] ;

[0065] It can be seen that the associated spatiotemporal range includes the associated time range and the set of its associated spatiotemporal range; at this time, both the time range and the space range are discontinuous; if the associated spatiotemporal range set of the detection point p is empty, it indicates that the detection point p cannot be used as a representative detection point;

[0066] Preferred: is the second relevance threshold; ;

[0067] Step S232: Based on time and space points The associated space-time range is reduced; specifically, the space-time points to be reduced are divided into the following three cases for processing;

[0068] Case 1: If , then the spatial and temporal range will be associated

[0069] Split into two associated space-time ranges

[0070] and ; At this time, the time-space points to be reduced do not involve the deletion of any detection points,

[0071] It only requires a reduction in the time frame;

[0072] Case 2: If and , then the spatial and temporal range will be associated Spatial range The detection point in Delete; at this time, the time and space points to be reduced do not involve time segmentation, only the spatial range needs to be reduced;

[0073] Case 3: If and , at this time, if ; then the space-time range will be associated Modified to associate time and space range or associated space-time range Otherwise, the space-time range will be associated Spatial range The detection point in Delete; Obviously, after splitting, deleting, and reducing the associated space-time range, steps S231 to S233 are repeated until the , or until it is deleted from the associated space-time range set;

[0074] Preferably: if the size of the associated spatiotemporal range obtained after reduction or deletion is smaller than the range size threshold, the associated spatiotemporal range obtained is deleted from the associated spatiotemporal range set; wherein: the size of the associated spatiotemporal range is equal to ;Range size threshold is a preset value;

[0075] Of course, when using this method for time-space reduction, each associated time-space range can be split into 4 associated time-space ranges for a single time-space point to achieve the deletion of a single time-space point, but this is actually complicated to operate and will bring about a large overhead for switching detection methods; it is suitable for situations with a small spatial range, a small number of detection points, and a low overall correlation;

[0076] Preferred: A set of detection points consisting of all detection points ,according to and / or To determine whether to select step S23 or its alternative 1; a typical way is that when When it is less than the irrelevant threshold, or When the number of detection points is greater than the threshold, the replacement method 1 is adopted to reduce the difficulty of the method in real time. Otherwise, step S23 is adopted. Another typical method is that when When it is less than the irrelevant threshold, alternative method 1 is adopted to reduce the difficulty of the method in real time, otherwise, step S23 is adopted;

[0077] The alternative method 2 of step S23 is a compromise method. In this case, step S23 is specifically to first reduce the space from the spatial range and then reduce the time from the time range. At this time, you can adjust value, so that it is between and Between; Applicable to situations where spatial correlation is stronger than temporal correlation, or the time range is relatively wide and the time granularity is large (large time segment);

[0078] Step S3: If the spatiotemporal range of one or more detection points can cover the entire spatiotemporal range, the set of one or more detection points is used as a fast detection point set, and the detection points in the fast detection point set are used for fast detection; specifically: if one or more detection points satisfy the following formula (10) or (11), the one or more detection points are used as a fast detection point set. As a collection of rapid detection points ;Will The minimum fast detection point set is used as the determined fast detection point set, and the detection points in the determined fast detection point set are used for fast detection; wherein: ;

[0079] ;

[0080] (11);

[0081] It can be seen that formula (11) is a relatively strict judgment condition, where: Indicates that the two elements before and after it have a strong association; that is, The element is followed by a restriction, which limits the elements that participate in the union. and Being in the same space-time scope; requiring temporal and spatial alignment in each associated space-time scope;

[0082] In the case of using the associated spatiotemporal range set, the step S3 is specifically as follows: if the union of the associated spatiotemporal range sets of one or more detection points can cover the entire spatiotemporal range, then the set of one or more detection points is used as a fast detection point set, and the detection points in the fast detection point set are used for fast detection; specifically, if one or more detection points satisfy the following formula (12) or (13), then the one or more detection points are used as a fast detection point set. As a collection of rapid detection points ;Will The minimum fast detection point set is used as the determined detection point set, and the detection points in the determined fast detection point set are used for fast detection; wherein: ;

[0083] ;

[0084] ;

[0085] It can be seen that formula (13) is a relatively strict judgment condition, which requires the time and space in each associated space-time range to be aligned, limiting the number of participants in the union. and Being in the same related space-time scope;

[0086] Further: when there are multiple rapid detection point sets, the one or more rapid detection point sets are sorted according to the sorting condition to form a rapid detection point set sequence; during the detection process, all detection points in the rapid detection point set are selected from the beginning to the end according to the order of the detection point set sequence for pollutant detection;

[0087] Preferably: before sorting, the rapid detection point set is completed, and detection points that are not associated with any detection point in the rapid detection point set are put into the rapid detection point set; this association is the association between detection data, the association of geographical locations, the association of detection point attributes, etc.;

[0088] The step of sorting the one or more detection point sets according to the sorting condition to form a rapid detection point set sequence specifically includes the following steps:

[0089] Step S3A1: For each fast detection point set, calculate each fast detection point set based on the fast detection point set size and time cost Score ; Specifically include the following steps:

[0090] Step S3A1_SUB1: Set time segment parameters , set the initial value of the time segment parameter to 1; set each fast detection point set Switching stability score The initial value is 0; set the score The initial value of is 0; is the next time segment; of course, The granularity can be set larger, for example, including multiple time segments t;

[0091] Step S3A1_SUB2: If Then Add to first set In; if Then Add to second set Calculate each fast detection point set based on the following formula (14): Switching stability score ;

[0092] (14);

[0093] When the detection points that actually play a role frequently switch over time, it indicates that the stability of the detection results is not strong and the representativeness of the fast detection point set is unstable. In addition, when the representativeness of the detection equipment changes over time, strategies such as sleep can be adopted for these detection points to save power consumption to avoid detection consumption. The lack of stability makes these saving strategies impossible to implement.

[0094] Step S3A1_SUB3: Calculate score based on switching stability score and fast detection point set ; Specifically: Calculate each fast detection point set based on the following formula (15): Score ;

[0095] (15);

[0096] Step S3A1_SUB4: Sort the fast detection point set according to the score from large to small to form a fast detection point set sequence; it can be seen that the larger the score, the stronger the switching stability, which may bring more opportunities for power saving; at the same time, the fewer the number of detection points that need to be started, the higher the detection speed and efficiency;

[0097] The sorting for the associated spatiotemporal range is similar. The set of scores for each related spatiotemporal range can be used as the score for the detection point p for sorting. Of course, in the actual sorting process, other conditions such as implementation difficulty and detection capability can be considered; they will not be elaborated here.

[0098] Of course, if switching stability is not considered, the score can be directly set to ;

[0099] Step S3A2: sorting the rapid detection point sets according to the order of scores from large to small to form a rapid detection point set sequence;

[0100] The use of the detection points in the rapid detection point set for rapid detection is specifically as follows: all detection points in the detection point set are started; all detection points in the detection point set are used for real-time detection; the correlation between the detection data obtained from all detection points and the detection data obtained from the detection points in the rapid detection point set is discovered through historical detection data, estimated detection data at the positions of all detection points are obtained based on the real-time detection data and the correlation, and pollutant treatment is performed based on the obtained estimated detection data; since the number of detection points in the rapid detection point set is usually much smaller than the number of detection points, the detection amount is greatly reduced by constructing the rapid detection point set, thereby achieving the effect of rapid detection;

[0101] Preferably: the detection data includes pollutants and their concentrations;

[0102] Preferably: when the detection data obtained by detecting the detection points in the rapid detection point set changes beyond the variation range, that is, when an abnormality occurs, the next rapid detection point set is selected from the rapid detection point set sequence for rapid detection; of course, the rapid detection point set with the largest difference from the current rapid detection point set can also be selected for rapid detection; alternatively: the detection data of all detection points are periodically acquired, and the correlation between the detection data of each detection point and the detection data of all detection points in the rapid detection point set is determined; if for each detection point, there is a detection point in the rapid detection point set that is correlated with each detection point, then switching is not required, otherwise, switching is required; find a rapid detection point set that meets the condition of "for each detection point, there is a detection point in the rapid detection point set that is correlated with each detection point" as the current rapid detection point set;

[0103] Further: based on historical detection data and attribute information of detection points, the corresponding relationship between detection point attribute information and rapid detection point set is obtained; when the attribute information of detection points changes, the rapid detection point set corresponding to the changed detection point attributes is obtained, and it is used as the current rapid detection point set for rapid detection; in this way, it is compatible with detection point attribute analysis, and combined with the rapid detection point set and the detection point attribute relationship, it is possible to quickly locate the best rapid detection point set in the rapid detection point set.

[0104] Preferably: using an artificial intelligence model to train to obtain the corresponding relationship between the detection point attribute data and the rapid detection point set;

[0105] Replaceable: When it is necessary to switch the fast detection point set, for abnormal situations, the detection technologies used in different detection points are considered. When the detection technologies used in the fast detection point set are very different, the switching may be more meaningful;

[0106] The method further comprises: step S4: for each pollutant type k, determining each detection point The covered spatiotemporal range; if the combination of the spatiotemporal range (associated spatiotemporal range set) of one or more detection points for each pollutant type k can cover the entire spatiotemporal range, then the set of multiple detection points is used as a rapid detection point set, and the detection points in the rapid detection point set are used for rapid detection; wherein: ; K is the number of pollutant types; that is, the coverage capacity after merging is judged for each pollutant type k. If there are one or more detection points that can cover the entire spatiotemporal range for all pollutant types, the set of multiple detection points is used as the rapid detection point set; of course, when there are multiple rapid detection point sets, the above-mentioned similar method is still used to obtain the score, and the appropriate rapid detection point set is selected for rapid monitoring;

[0107] By comprehensively considering the detection capabilities of different detection points for pollutant types, it is possible to achieve rapid detection from the perspective of practical operation, the cost capacity of detection equipment, and the full coverage of detection types and detection space coverage capabilities, by reducing the number of detection points that need to be tested in real time.

[0108] Based on the same inventive concept, the present invention also provides a rapid pollutant detection system, which is used to complete the above-mentioned rapid pollutant detection method; the rapid pollutant detection system is arranged on a server; a detection device is arranged at the detection point to detect different types of pollutants and their concentrations; the detection device can screen and identify non-targeted organic matter, using MZmine, XCMS, etc. to process mass spectrometry data, identify and quantify compounds, and can also use compound databases such as ChemSpider and PubChem for compound matching and identification; of course, technical support is required during the detection process: of course, it is necessary to follow environmental detection standards, such as national and international water quality detection standards, to ensure the accuracy and reliability of the detection data;

[0109] Preferably: a wireless communication device is provided at the detection point to send real-time detection data to a pollutant rapid detection system located at the server side;

[0110] Preferably: the server is a cloud server;

[0111] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of a programming language, including an assembled or interpreted language, a declarative or procedural language, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0112] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for rapid detection of pollutants, characterized in that: The method comprises: Step S1: Deploy detection points in the pollution prevention and control area To form a set of detection points , the detection point is equipped with a detection device capable of detecting pollutants and obtaining detection data; historical detection data are collected and divided into T segments, and for the detection data within each segment time t, its characteristic value is used as the detection data of the segment t; wherein: ; Step S2: Determine each detection point The time and space range covered; repeat this step until all detection points All processing has been completed; the specific steps include the following: Step S21: Setting the detection point The current space-time range The initial value is ;in: is the time range, is the set of all detection points, which constitutes the complete spatial range; Step S22: Obtain an unprocessed detection point and its current time and space range; use formula (1) (2) to calculate different detection points The spatiotemporal correlation coefficient of the detection data ;in: The time Time detection point Detection data at is the neighbor weight; is the set of detection points Number of detection points; ; Is to seek The number of elements in ; (1)； (2)； Step S23: If , then the current space-time range As the space-time range of the detection point p , go to step S3; otherwise, perform time-space reduction in three directions; the first direction The current time range Time Set as the time point to be reduced, and use formula (5) to calculate the first temporary coefficient , the second direction Is the time point Set as the time point to be reduced, and use formula (6) to calculate the second temporary coefficient ; Third party The current spatial range middle The smallest value Set as the spatial point to be reduced, and use formula (7) to calculate the third temporary coefficient ;in: , ⊆ ; is the first correlation threshold; repeat steps S22 and S23 until all detection points Until all processing is completed; (5)； (6) (7)； Will The corresponding direction is used as the time-space reduction direction, and the time point to be reduced or the space point to be reduced corresponding to the time-space reduction direction is deleted from the current time-space range to update the current time-space range; returning to step S22; Step S3: If the spatiotemporal range of one or more detection points can cover the entire spatiotemporal range, the set of one or more detection points is used as a fast detection point set, and the detection points in the fast detection point set are used for fast detection; specifically: if one or more detection points satisfy the following formula (10), the one or more detection points are used as a fast detection point set. As a collection of rapid detection points ;Will The minimum fast detection point set is used as the determined fast detection point set, and the detection points in the determined fast detection point set are used for fast detection; wherein: ; （10）。 2. The rapid detection method for pollutants according to claim 1, characterized in that: The historical detection data is big data information.

3. The rapid detection method for pollutants according to claim 2, characterized in that: The characteristic value is an average value, a typical value, a maximum value and / or a minimum value.

4. The rapid detection method for pollutants according to claim 3, characterized in that: The detection point is provided with a pollutant detection device capable of detecting K types of pollutants, where K is a preset value.

5. The rapid detection method for pollutants according to claim 4, characterized in that: The detection point is used for online rapid analysis of perfluorinated compounds, pesticides, and antibiotics in agricultural irrigation areas and screening and identification of non-targeted organic matter.

6. The rapid detection method for pollutants according to claim 5, characterized in that: The detection device is a high-resolution mass spectrometer.

Images