Environmental pollution source automatic monitoring facility field mobile inspection terminal and system and method

Abstract

The application discloses an environmental pollution source automatic monitoring facility field mobile inspection terminal and system and method, relates to the technical field of environmental protection, and solves the technical problem that the prior art monitors fixed areas and lacks consideration of pollution source positioning after pollution occurs, so that the efficiency of environmental pollution source monitoring is relatively low; an abnormality detection coefficient is generated according to detection data; a state label is generated according to the abnormality detection coefficient and an abnormal area is generated accordingly; a regional abnormality coefficient is calculated according to the abnormal area; an alarm signal is generated according to the regional abnormality coefficient; a detection point corresponding to the highest value of the abnormality detection coefficient is acquired as a starting detection point, a pollution source area is positioned according to the starting detection point and environmental data, each index affecting water quality is taken as a key parameter for abnormality detection, and each abnormality detection point is used to adaptively obtain an abnormal area, so that the efficiency and accuracy of automatic abnormality detection are improved, the pollution source area is adaptively found in the abnormal area, and the work efficiency is improved.

Description

Technical Field

[0001] This application belongs to the field of environmental protection technology, specifically to the on-site mobile inspection terminal, system and method for automatic monitoring facilities of environmental pollution sources. Background Technology

[0002] Environmental pollution sources are a broad concept, referring to the sources of pollutants that cause environmental pollution. Pollution sources typically refer to places, equipment, devices, or individuals that discharge harmful substances into the environment or have harmful effects on it. These harmful substances or energies enter the environmental system at inappropriate concentrations, quantities, rates, forms, and pathways, causing pollution or damage. Major pollution sources include industrial pollution sources, agricultural pollution sources, transportation pollution sources, and domestic pollution sources. Water pollution, as one of the most urgent problems to be solved in the current pollution situation, seriously affects people's lives and the state of the ecological environment.

[0003] The prior art (patent application CN114217032A) discloses a water quality environment detection method and system, wherein the water quality environment detection system includes at least one water quality detection module, a measurement and control terminal connected to the water quality detection module, a database and video data storage module connected to the measurement and control terminal, as well as a cloud monitoring platform and a water environment management application platform; the system collects data through the measurement and control terminal and transmits it to the database and video data storage module for storage, and then analyzes and evaluates the data through the water environment management application platform to promptly grasp the water quality status and provide early warning and forecasting of major water pollution accidents.

[0004] The aforementioned cases utilize cloud monitoring platforms and water environment management application platforms to continuously monitor water bodies in the target area 24 hours a day. The water quality is then analyzed and evaluated through the water environment management application platform to promptly grasp the water quality status. However, these cases lack consideration for locating pollution sources after pollution occurs, and they only target fixed areas for detection, failing to automatically detect random areas, resulting in low efficiency in environmental pollution source monitoring. Therefore, further improvements are needed for the automatic inspection system for environmental pollution sources. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes an on-site mobile inspection terminal, system and method for automatic monitoring facilities of environmental pollution sources, to solve the technical problem that the prior art monitors fixed areas and lacks consideration for the location of pollution sources after pollution occurs, resulting in low efficiency of environmental pollution source monitoring.

[0006] To achieve the above objectives, the first aspect of this application provides a mobile on-site inspection system for automatic monitoring facilities of environmental pollution sources, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0007] The data acquisition module acquires detection data, environmental data, and coordinate data of several detection points through a data acquisition device.

[0008] The data analysis module: generates an anomaly coefficient based on the detection data; generates a status label for each detection point based on the anomaly coefficient of each detection point and uses this label to generate an anomaly area; calculates the anomaly coefficient of the area based on the anomaly area; generates an alarm signal based on the anomaly coefficient of the area; obtains the detection point corresponding to the highest value of the anomaly coefficient as the starting detection point, and locates the pollution source area based on the starting detection point and environmental data.

[0009] The early warning module: provides prompts based on alarm signals and contacts management personnel.

[0010] This application generates anomaly coefficients based on detection data and status labels for each detection point based on the anomaly coefficients described above, thereby generating anomaly regions. It uses various indicators affecting water quality as key parameters for anomaly detection and adaptively obtains anomaly regions from each anomaly detection point, improving the efficiency and accuracy of automatic anomaly detection. At the same time, it locates pollution source areas based on the starting detection point and environmental data, and adaptively searches for the pollution source range within the anomaly region, accelerating the process of finding pollution sources and improving work efficiency.

[0011] Furthermore, the step of generating anomaly coefficients based on detection data includes:

[0012] Obtain several testing items at the testing point, their corresponding test values, and the corresponding standard safety ranges;

[0013] The testing items are divided into two groups based on the standard safety range: Group 1 and Group 2. Group 1 includes testing items whose standard safety range has only an upper or lower limit value. Group 2 includes testing items whose standard safety range has both an upper and lower limit value.

[0014] Anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 are generated based on detection project group 1 and detection project group 2;

[0015] The detection anomaly coefficient JYX of the detection point is calculated using the formula JYX=YX1+YX2.

[0016] This application improves the accuracy of the detection anomaly coefficient of the detection points by grouping the detection items according to their corresponding standard safety ranges and calculating them separately based on the characteristics of each group. This also increases the calculation efficiency.

[0017] Furthermore, the generation of anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 based on detection item group 1 and detection item group 2 includes:

[0018] Extract the detection values ​​(JS) corresponding to several detection items in Detection Item Group 1. i The corresponding upper or lower limit value (DXZ) in the standard safety range. i The detection values ​​JS corresponding to several detection items in Detection Project Group 2 j The corresponding upper and lower limits of the standard safety range;

[0019] The standard safety median value BAZ is generated based on the upper and lower limits of the standard safety range. j and floating deviation FP j ;

[0020] Check each JS in turn i and JS j Whether it falls within its corresponding standard safety range;

[0021] Yes, set the outlier coefficient of the detected value to "0", i.e., YZX1 i =0, YZX2 j =0;

[0022] No, through formula Calculate the outlier coefficient YZX1 for each test item in Test Item Group 1. i ;

[0023] Through formula Calculate the outlier coefficient YZX2 for each test item in Test Item Group 2. j ; where β1 i and β2 j β1 is the exponential coefficient. i and β2 j ∈(0,1);DX1 i and DX2 j These are the unit data for the i-th test item in test item group one and the j-th test item in test item group two, respectively.

[0024] Using the formula YX1=Σ i γ1 i ×YZX1 i And YX2=Σ j γ2 j ×YZX2 j Calculate anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2; where γ1 i and γ2 j γ1 is the weighting coefficient, and γ1 i and γ2 j ∈(0,1).

[0025] Furthermore, the step of generating the standard safety intermediate value BAZ based on the upper and lower limits of the standard safety range... j and floating deviation FP j ,include:

[0026] Mark the upper limit of the standard safety range corresponding to the test item numbered j as BAFD. j The lower limit value is marked as BAFX j ;

[0027] Through the formula BAZ j = (BAFD) j +BAFX j ) / 2 Calculate the standard safety median value (BAZ) for several test data. j ;

[0028] Through the formula FP j = (BAFD) j -BAFX j ) / 2 calculates the floating deviation FP of several detection data. j .

[0029] Furthermore, the step of generating detection point status labels based on the detection anomaly coefficients of each detection point and using these labels to generate anomaly regions includes:

[0030] Obtain the detection anomaly coefficient and coordinate data for each detection point;

[0031] Determine whether the detection anomaly coefficient is greater than the anomaly threshold; if yes, set the detection point as an anomaly label; if no, set the detection point as a normal label.

[0032] Extract the coordinate data of the detection points that are normal labels;

[0033] Convex polygons were constructed as anomalous regions using the Graham scan method.

[0034] Furthermore, the calculation of the regional anomaly coefficient based on the anomaly region includes:

[0035] Obtain the abnormal area S of the abnormal region and the detection anomaly coefficient JYX of several detection points within the abnormal region. b ;

[0036] Through formula Calculate the regional anomaly coefficient QYX; where α1 and α2 are weighting coefficients, α1 and α2∈(0,1); DS is the unit area.

[0037] Furthermore, the step of generating an alarm signal based on the regional anomaly coefficient includes:

[0038] Obtain the regional anomaly coefficient, anomaly area, and several detection anomaly coefficients;

[0039] Determine whether the regional anomaly coefficient is greater than the regional anomaly threshold;

[0040] Yes, it generates a severe pollution warning signal for the area;

[0041] No, determine if the abnormal area is greater than the area threshold; yes, generate a severe pollution spread alarm signal; no, do nothing.

[0042] Determine if there is an anomaly coefficient greater than the detection threshold; if yes, generate a pollution alarm signal; otherwise, do nothing.

[0043] Furthermore, the process of locating the pollution source area based on the initial detection point and environmental data includes the following steps:

[0044] Step 1: Obtain the coordinate data of the starting detection point, the detection anomaly coefficient JYX, and the water flow velocity SV from the environmental data;

[0045] Step 2: Calculate the moving distance YJ using the formula YJ=BYJ×(1+ln(SV+1)); where BYJ represents the standard moving distance; with the coordinates of the starting detection point as the center and the moving distance as the radius, set several surrounding detection points according to the moving direction; when the surrounding detection points exceed the abnormal area, the intersection with the abnormal area is taken as the surrounding detection points;

[0046] Step 3: Calculate the detection anomaly coefficients JYXc around several detection points; where c represents the number of the detection point; c = 1, 2, ..., Q; Q is the total number of detection points; determine whether there are any detection anomaly coefficients around detection points that are greater than the detection anomaly coefficient of the initial detection point;

[0047] Yes, set the coordinate position corresponding to the maximum value among several detection anomaly coefficients surrounding the detection point as the starting detection point and proceed to step one; no, proceed to step four.

[0048] Step 4: Using the starting detection point as the center and the distance R as the radius, construct the pollution source area.

[0049] This application uses the detection point corresponding to the highest detection anomaly coefficient within an abnormal region as the starting detection point, and adaptively finds the coordinates of the location with the highest detection anomaly coefficient within the abnormal region to construct the pollution source area. This provides strong support for users to find pollution sources, accelerates the process of finding pollution sources, and improves work efficiency.

[0050] A second aspect of the present invention provides a method for on-site mobile inspection of automatic monitoring facilities for environmental pollution sources, comprising:

[0051] S0: Acquire detection data, environmental data, and coordinate data for several detection points;

[0052] S1: Generate anomaly coefficients based on the detection data; generate status labels for each detection point based on the anomaly coefficients of each detection point, and generate anomaly regions accordingly;

[0053] S2: Calculate the regional anomaly coefficient based on the abnormal area; generate an alarm signal based on the regional anomaly coefficient;

[0054] S3: Obtain the detection point corresponding to the highest value of the detection anomaly coefficient as the starting detection point, and locate the pollution source area based on the starting detection point and environmental data;

[0055] S4: Prompt an alert based on the alarm signal and contact management personnel.

[0056] Another aspect of the present invention provides a mobile on-site inspection terminal for automatic monitoring facilities of environmental pollution sources, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0057] Compared with the prior art, the beneficial effects of this application are:

[0058] 1. This application generates anomaly coefficients based on detection data; generates status labels for each detection point based on the anomaly coefficients of each detection point and uses these labels to generate anomaly areas; calculates the regional anomaly coefficients based on the anomaly areas; generates alarm signals based on the regional anomaly coefficients; obtains the detection point corresponding to the highest value of the anomaly coefficient as the starting detection point; locates the pollution source area based on the starting detection point and environmental data; performs anomaly detection using various indicators affecting water quality as key parameters; and adaptively obtains anomaly areas from each anomaly detection point, thereby improving the efficiency and accuracy of automatic anomaly detection. It also adaptively finds pollution source areas within the anomaly areas, improving work efficiency.

[0059] 2. This application improves the accuracy of the detection anomaly coefficient of the detection points by grouping the detection items according to their corresponding standard safety ranges and calculating them separately according to the characteristics of each group. This also improves the calculation efficiency.

[0060] 3. This application uses the detection point corresponding to the highest detection anomaly coefficient in the abnormal area as the starting detection point, and adaptively finds the location coordinates of the highest detection anomaly coefficient in the abnormal area to construct the pollution source area, thereby providing strong support for users to find pollution sources, accelerating the process of finding pollution sources, and improving work efficiency. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a schematic diagram of the on-site mobile inspection system for automatic monitoring facilities of environmental pollution sources in this application;

[0063] Figure 2 This is a flowchart of the method for locating pollution source areas in this application;

[0064] Figure 3 This is a flowchart of the on-site mobile inspection method for automatic monitoring facilities of environmental pollution sources in this application. Detailed Implementation

[0065] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0066] Please see Figure 1 The first aspect of this application provides a mobile on-site inspection system for automatic monitoring facilities of environmental pollution sources, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0067] Data acquisition module: Acquires detection data, environmental data, and coordinate data from several detection points through data acquisition equipment; the data acquisition equipment includes various sensors, etc.; the detection data includes several detection items and their corresponding detection values;

[0068] Data Analysis Module: Generates detection anomaly coefficients based on detection data, which indicate the degree of anomaly at each detection point; generates status labels for each detection point based on its detection anomaly coefficient, and uses these labels to generate anomaly regions; calculates regional anomaly coefficients based on the anomaly regions, which indicate the degree of anomaly in the anomaly regions; generates alarm signals based on the regional anomaly coefficients; obtains the detection point corresponding to the highest detection anomaly coefficient value as the starting detection point, and locates the pollution source area based on the starting detection point and environmental data.

[0069] Early warning module: Provides prompts based on alarm signals and contacts management personnel; alarm signals include regional severe pollution alarm signals, severe pollution spread alarm signals, and pollution presence alarm signals, etc.

[0070] In this embodiment, generating anomaly coefficients based on detection data includes:

[0071] Obtain several testing items at the testing point, their corresponding test values, and the corresponding standard safety ranges;

[0072] The testing items are divided into two groups based on the standard safety range: Group 1 and Group 2. Group 1 includes testing items whose standard safety range has only an upper or lower limit value. Group 2 includes testing items whose standard safety range has both an upper and lower limit value.

[0073] Anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 are generated based on test item group 1 and test item group 2; anomaly coefficient 1 and anomaly coefficient 2 refer to the degree of anomaly of test item group 1 and test item group 2.

[0074] The detection anomaly coefficient JYX of the detection point is calculated using the formula JYX=YX1+YX2; the detection anomaly coefficient of the detection point increases as the anomaly coefficient one and anomaly coefficient two of the detection point increase.

[0075] This embodiment groups the test data according to the test items in the test data, uses the standard safety range corresponding to the test items as the dividing standard, calculates the anomaly coefficient of each group separately, and merges them to finally obtain the test anomaly coefficient of the test point. The calculation is performed separately according to the characteristics of each group of test items, which greatly improves the calculation efficiency.

[0076] In this embodiment, generating anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 based on detection item group 1 and detection item group 2 includes:

[0077] Extract the detection values ​​(JS) corresponding to several detection items in Detection Item Group 1. i The corresponding upper or lower limit value (DXZ) in the standard safety range. i JS corresponding to several testing items in Testing Project Group 2 j The corresponding upper and lower limits of the standard safety range;

[0078] The standard safety median value BAZ is generated based on the upper and lower limits of the standard safety range. j and floating deviation FP j The standard safety median value refers to the value that is in the middle of the standard safety range; the fluctuation deviation refers to the distance between the standard safety median value and the boundary of the standard safety range.

[0079] Check each JS in turn i and JS j Whether it falls within its corresponding standard safety range;

[0080] Yes, set the outlier coefficient of the detected value to "0", i.e., YZX1 i =0, YZX2 j =0;

[0081] No, through formula Calculate the outlier coefficient YZX1 for each test item in Test Item Group 1. i The more a test value in test item group one deviates from its corresponding standard safety range, the more serious the abnormal state of the test item corresponding to that test value; therefore, the abnormal value coefficient of each test item in test item group one increases accordingly.

[0082] Through formula Calculate the outlier coefficient YZX2 for each test item in Test Item Group 2. j ; where β1 i and β2 j β1 is the exponential coefficient. i and β2 j ∈(0,1), the specific value is set based on experience; DX1 i and DX2 j These are the unit data for the i-th test item in test item group one and the j-th test item in test item group two, respectively. The specific values ​​are set based on experience. The more each test value in test item group two deviates from its corresponding standard safety range, the more serious the abnormal state of the test item corresponding to that test value is. Therefore, the abnormal value coefficient of each test item in test item group two increases accordingly.

[0083] Using the formula YX1=Σ i γ1 i ×YZX1 i And YX2=Σ j γ2 j ×YZX2 j Calculate anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2; where γ1 i and γ2 j γ1 is the weighting coefficient, and γ1 i and γ2 j ∈(0,1), the specific value is set according to experience; the anomaly coefficients corresponding to detection item group one and detection item group two increase as the anomaly coefficient in the detection item group increases.

[0084] In this embodiment, the standard safety intermediate value BAZ is generated based on the upper and lower limits of the standard safety range. j and floating deviation FP j ,include:

[0085] Mark the upper limit of the standard safety range corresponding to the test item numbered j as BAFD.j The lower limit value is marked as BAFX j ;

[0086] Through the formula BAZ j = (BAFD) j +BAFX j ) / 2 Calculate the standard safety median value (BAZ) for several test data. j The standard safety median value increases as its corresponding upper and lower limits increase.

[0087] Through the formula FP j = (BAFD) j -BAFX j ) / 2 calculates the floating deviation FP of several detection data. j The larger the standard safety range, the greater the corresponding fluctuation deviation.

[0088] In this embodiment, generating detection point status labels based on the detection anomaly coefficients of each detection point and using these labels to generate abnormal regions includes:

[0089] Obtain the detection anomaly coefficient and coordinate data for each detection point; the coordinate data includes two-dimensional coordinates and three-dimensional coordinates, etc.

[0090] Determine whether the detection anomaly coefficient is greater than the anomaly threshold, which is set based on experience; if yes, set the detection point as an anomaly label; otherwise, set the detection point as a normal label.

[0091] The coordinate data of the detection points are extracted from the normal labels; in this embodiment, the coordinate data uses two-dimensional coordinates.

[0092] Convex polygons were constructed as anomalous regions using the Graham scan method.

[0093] In this embodiment, a status label is set for each detection point by detecting anomaly coefficients. For each detection point with an abnormal label status, an abnormal region is constructed using the Graham scanning method. The abnormal region changes adaptively with the coordinate data of the abnormal label detection point, thereby improving the accuracy and efficiency of abnormal region generation.

[0094] In this embodiment, calculating the regional anomaly coefficient based on the anomaly region includes:

[0095] Obtain the abnormal area S of the abnormal region and the detection anomaly coefficient JYX of several detection points within the abnormal region. b ;

[0096] Through formula Calculate the regional anomaly coefficient QYX; where α1 and α2 are weighting coefficients, α1 and α2∈(0,1), and the specific values ​​are set according to experience; DS is the unit area, and the specific value is set according to experience. In this embodiment, DS is set to 1㎡; the larger the abnormal area within the abnormal region, the more serious the pollution in the abnormal region; similarly, the larger the average detection anomaly coefficient of each detection point within the abnormal region, the more serious the pollution in the abnormal region; therefore, the regional anomaly coefficient increases with the increase of the abnormal area and the average detection anomaly coefficient.

[0097] In this embodiment, generating an alarm signal based on the regional anomaly coefficient includes:

[0098] Obtain the regional anomaly coefficient, anomaly area, and several detection anomaly coefficients;

[0099] Determine whether the regional anomaly coefficient is greater than the regional anomaly threshold, which is set based on experience.

[0100] Yes, it generates a severe pollution warning signal for the area;

[0101] No, determine if the abnormal area is greater than the area threshold, which is set based on experience; yes, generate a severe pollution spread alarm signal; no, do nothing.

[0102] Determine if there is an anomaly coefficient greater than the detection threshold, which is set based on experience; if yes, generate a pollution alarm signal; otherwise, do nothing.

[0103] Please see Figure 2 In this embodiment, locating the pollution source area based on the starting detection point and environmental data includes the following steps:

[0104] Step 1: Obtain the coordinate data of the starting detection point, the detection anomaly coefficient JYX, and the water flow velocity SV from the environmental data;

[0105] Step 2: Calculate the moving distance YJ using the formula YJ = BYJ × (1 + ln(SV + 1)); where BYJ represents the standard moving distance, and the specific value is set based on experience. In this embodiment, BYJ is set to 1m. Using the coordinates of the starting detection point as the center and the moving distance as the radius, set several surrounding detection points according to the moving direction. When the surrounding detection points exceed the abnormal area, the intersection with the abnormal area is taken as the surrounding detection point. In this embodiment, eight moving directions are set, divided into east, south, west, north, southeast, northeast, southwest, and northwest. The faster the water flow, the farther the pollutants can spread in a short time, thus increasing the moving distance. When the water flow is 0, i.e., the water surface is stationary, the moving distance is the standard moving distance.

[0106] Step 3: Calculate the detection anomaly coefficients JYXc around the detection points; where c represents the number of the detection points; c = 1, 2, ..., Q; Q is the total number of detection points; in this embodiment, Q is set to 8; determine whether there are any detection anomaly coefficients around the detection points that are greater than the detection anomaly coefficient of the starting detection point;

[0107] Yes, set the coordinate position corresponding to the maximum value among several detection anomaly coefficients surrounding the detection point as the starting detection point and proceed to step one; no, proceed to step four.

[0108] Step 4: Using the starting detection point as the center and the distance R as the radius, construct the pollution source area; the distance R is set based on experience.

[0109] This embodiment uses the detection point corresponding to the highest anomaly coefficient within the abnormal area as the starting detection point. Each time, it selects the surrounding detection point with the highest anomaly coefficient from the surrounding detection points around the starting detection point as the starting detection point for the next cycle, until the detection point with the final anomaly coefficient is found. This constructs the pollution source area, narrows the search range for pollution sources, improves work efficiency, and enhances the user experience.

[0110] Please see Figure 3 The second aspect of this application provides a method for on-site mobile inspection of automatic monitoring facilities for environmental pollution sources, including:

[0111] S0: Acquire detection data, environmental data, and coordinate data for several detection points;

[0112] S1: Generate anomaly coefficients based on the detection data; generate status labels for each detection point based on the anomaly coefficients of each detection point, and generate anomaly regions accordingly;

[0113] S2: Calculate the regional anomaly coefficient based on the abnormal area; generate an alarm signal based on the regional anomaly coefficient;

[0114] S3: Obtain the detection point corresponding to the highest value of the detection anomaly coefficient as the starting detection point, and locate the pollution source area based on the starting detection point and environmental data;

[0115] S4: Prompt an alert based on the alarm signal and contact management personnel.

[0116] Another embodiment of this application provides a mobile on-site inspection terminal for automatic monitoring facilities of environmental pollution sources, including: a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0117] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0118] The working principle of this application is as follows: It acquires detection data, environmental data, and coordinate data from several detection points; generates anomaly coefficients based on the detection data; generates status labels for each detection point based on its anomaly coefficient, and uses these labels to generate anomaly areas; calculates the area anomaly coefficient based on the anomaly area; generates an alarm signal based on the area anomaly coefficient; obtains the detection point corresponding to the highest anomaly coefficient as the starting detection point; locates the pollution source area based on the starting detection point and environmental data; issues a prompt based on the alarm signal and contacts management personnel; performs anomaly detection using various indicators affecting water quality as key parameters; and adaptively obtains anomaly areas from each anomaly detection point, improving the efficiency and accuracy of automatic anomaly detection. It adaptively locates pollution source areas within anomaly areas, improving work efficiency and avoiding the problems of existing technologies that monitor fixed areas and lack consideration for locating pollution sources after pollution occurs, resulting in low efficiency in environmental pollution source monitoring.

[0119] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A mobile on-site inspection system for automatic monitoring facilities of environmental pollution sources, characterized in that, include: Data acquisition module, data analysis module, early warning module, and database; The data acquisition module acquires detection data, environmental data, and coordinate data of several detection points through a data acquisition device. The data analysis module: generates an anomaly coefficient based on the detection data; generates a status label for each detection point based on the anomaly coefficient of each detection point, and uses this label to generate an anomaly region; Calculate the regional anomaly coefficient based on the abnormal area; generate an alarm signal based on the regional anomaly coefficient; The detection point corresponding to the highest value of the anomaly coefficient is used as the starting detection point, and the pollution source area is located based on the starting detection point and environmental data. The early warning module: issues a prompt based on the alarm signal and contacts the management personnel; The step of generating anomaly coefficients based on detection data includes: Obtain several testing items at the testing point, their corresponding test values, and the corresponding standard safety ranges; The testing items are divided into two groups based on the standard safety range: Group 1 and Group 2. Group 1 includes testing items whose standard safety range has only an upper or lower limit value. Group 2 includes testing items whose standard safety range has both an upper and lower limit value. Anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 are generated based on detection project group 1 and detection project group 2; The detection anomaly coefficient of the detection point is obtained by summing the anomaly coefficient one and the anomaly coefficient two. The generation of anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 based on detection item group 1 and detection item group 2 includes: Extract the detection values ​​corresponding to several detection items in Detection Item Group 1. The corresponding upper or lower limit value in the standard safety range. The test values ​​corresponding to several test items in Test Item Group 2 The corresponding upper and lower limits of the standard safety range; Generate standard safety intermediate values ​​based on the upper and lower limits of the standard safety range. and floating deviation ; Judge each one in turn and Whether it falls within its corresponding standard safety range; Yes, the outlier coefficient of the detected value is set to "0", that is... , ; No, through formula Calculate the outlier coefficients for each test item in Test Item Group 1. ; Through formula Calculate the outlier coefficients for each test item in Test Item Group 2. ;in, and For exponential coefficients, and ∈(0,1); and These are the unit data for the i-th test item in test item group one and the j-th test item in test item group two, respectively. Through formula and Calculate anomaly coefficient one YX1 and anomaly coefficient two YX2; where, and These are the weighting coefficients, and and ∈(0,1); The calculation of the regional anomaly coefficient based on the anomaly region includes: Obtain the abnormal area S of the abnormal region and the detection abnormality coefficient of several detection points within the abnormal region. ; Through formula Calculate the regional anomaly coefficient QYX; where, and These are the weighting coefficients. and ∈(0,1); DS is the unit area; The process of locating the pollution source area based on the initial detection point and environmental data includes the following steps: Step 1: Obtain the coordinate data of the starting detection point, the detection anomaly coefficient JYX, and the water flow velocity SV from the environmental data; Step Two: Using the formula Calculate the movement distance YJ; where BYJ represents the standard movement distance; with the coordinates of the starting detection point as the center and the movement distance as the radius, set several surrounding detection points according to the movement direction; when the surrounding detection points exceed the abnormal area, the intersection with the abnormal area is taken as the surrounding detection points; Step 3: Calculate the detection anomaly coefficients JYXc around several detection points; where c represents the number of the detection point; c = 1, 2, ..., Q; Q is the total number of detection points; determine whether there are any detection anomaly coefficients around detection points that are greater than the detection anomaly coefficient of the initial detection point; Yes, set the coordinate position corresponding to the maximum value among several detection anomaly coefficients surrounding the detection point as the starting detection point and proceed to step one; no, proceed to step four. Step 4: Using the starting detection point as the center and the distance R as the radius, construct the pollution source area.

2. The on-site mobile inspection system for automatic monitoring facilities of environmental pollution sources according to claim 1, characterized in that, The standard safety intermediate value is generated based on the upper and lower limits of the standard safety range. and floating deviation ,include: Mark the upper limit of the standard safety range corresponding to the test item numbered j as... The lower limit value is marked as ; The standard safety median value for several test data is obtained by taking half of the sum of the corresponding upper and lower limits. ; The fluctuation deviation of several detection data points is obtained by taking half of the difference between the corresponding upper and lower limits. .

3. The on-site mobile inspection system for automatic monitoring facilities of environmental pollution sources according to claim 1, characterized in that, The step of generating detection point status labels based on the detection anomaly coefficients of each detection point and generating anomaly regions accordingly includes: Obtain the detection anomaly coefficient and coordinate data for each detection point; Determine whether the detection anomaly coefficient is greater than the anomaly threshold; if yes, set the detection point as an anomaly label; if no, set the detection point as a normal label. Extract the coordinate data of the detection points that are normal labels; Convex polygons were constructed as anomalous regions using the Graham scan method.

4. The on-site mobile inspection system for automatic monitoring facilities of environmental pollution sources according to claim 1, characterized in that, The generation of alarm signals based on regional anomaly coefficients includes: Obtain the regional anomaly coefficient, anomaly area, and several detection anomaly coefficients; Determine whether the regional anomaly coefficient is greater than the regional anomaly threshold; Yes, it generates a severe pollution warning signal for the area; No, determine if the abnormal area is greater than the area threshold; yes, generate a severe pollution spread alarm signal; no, do nothing. Determine if there is an anomaly coefficient greater than the detection threshold; if yes, generate a pollution alarm signal; otherwise, do nothing.

5. A method for on-site mobile inspection of automatic monitoring facilities for environmental pollution sources, applied to the on-site mobile inspection system for automatic monitoring facilities for environmental pollution sources as described in any one of claims 1-4, characterized in that, include: S0: Acquire detection data, environmental data, and coordinate data for several detection points; S1: Generate anomaly coefficients based on the detection data; generate status labels for each detection point based on the anomaly coefficients of each detection point, and generate anomaly regions accordingly; S2: Calculate the regional anomaly coefficient based on the abnormal area; generate an alarm signal based on the regional anomaly coefficient; S3: Obtain the detection point corresponding to the highest value of the detection anomaly coefficient as the starting detection point, and locate the pollution source area based on the starting detection point and environmental data; S4: Issue a notification based on the alarm signal and contact management personnel; The step of generating anomaly coefficients based on detection data includes: Obtain several testing items at the testing point, their corresponding test values, and the corresponding standard safety ranges; The testing items are divided into two groups based on the standard safety range: Group 1 and Group 2. Group 1 includes testing items whose standard safety range has only an upper or lower limit value. Group 2 includes testing items whose standard safety range has both an upper and lower limit value. Anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 are generated based on detection project group 1 and detection project group 2; The detection anomaly coefficient of the detection point is obtained by summing the anomaly coefficient one and the anomaly coefficient two. The generation of anomaly coefficient 1 YX1 and anomaly coefficient 2 YX2 based on detection item group 1 and detection item group 2 includes: Extract the detection values ​​corresponding to several detection items in Detection Item Group 1. The corresponding upper or lower limit value in the standard safety range. The test values ​​corresponding to several test items in Test Item Group 2 The corresponding upper and lower limits of the standard safety range; Generate standard safety intermediate values ​​based on the upper and lower limits of the standard safety range. and floating deviation ; Judge each one in turn and Whether it falls within its corresponding standard safety range; Yes, the outlier coefficient of the detected value is set to "0", that is... , ; No, through formula Calculate the outlier coefficients for each test item in Test Item Group 1. ; Through formula Calculate the outlier coefficients for each test item in Test Item Group 2. ;in, and For exponential coefficients, and ∈(0,1); and These are the unit data for the i-th test item in test item group one and the j-th test item in test item group two, respectively. Through formula and Calculate anomaly coefficient one YX1 and anomaly coefficient two YX2; where, and These are the weighting coefficients, and and ∈(0,1); The calculation of the regional anomaly coefficient based on the anomaly region includes: Obtain the abnormal area S of the abnormal region and the detection abnormality coefficient of several detection points within the abnormal region. ; Through formula Calculate the regional anomaly coefficient QYX; where, and These are the weighting coefficients. and ∈(0,1); DS is the unit area; The process of locating the pollution source area based on the initial detection point and environmental data includes the following steps: Step 1: Obtain the coordinate data of the starting detection point, the detection anomaly coefficient JYX, and the water flow velocity SV from the environmental data; Step Two: Using the formula Calculate the movement distance YJ; where BYJ represents the standard movement distance; with the coordinates of the starting detection point as the center and the movement distance as the radius, set several surrounding detection points according to the movement direction; when the surrounding detection points exceed the abnormal area, the intersection with the abnormal area is taken as the surrounding detection points; Step 3: Calculate the detection anomaly coefficients JYXc around several detection points; where c represents the number of the detection point; c = 1, 2, ..., Q; Q is the total number of detection points; determine whether there are any detection anomaly coefficients around detection points that are greater than the detection anomaly coefficient of the initial detection point; Yes, set the coordinate position corresponding to the maximum value among several detection anomaly coefficients surrounding the detection point as the starting detection point and proceed to step one; no, proceed to step four. Step 4: Using the starting detection point as the center and the distance R as the radius, construct the pollution source area.

6. A mobile on-site inspection terminal for automatic monitoring facilities of environmental pollution sources, applied to the mobile on-site inspection system for automatic monitoring facilities of environmental pollution sources as described in any one of claims 1-4, characterized in that, include: A memory, a processor, and a computer program stored in the memory and capable of running on the processor.

Images