Intelligent analysis system for river patrol data based on big data

Abstract

This invention discloses an intelligent analysis system for river patrol data based on big data. This invention relates to the field of river patrol technology and solves the problem of assessing the existence of momentum risks in corresponding river areas without based on specific patrol data. The invention uses a river feature processing terminal to equally divide the river contour model according to differences in contour length. Through volume parameter analysis, it identifies regions with the same characteristics and divides them into different feature zones, simplifying the complex river contour into multiple clearly defined regions for targeted analysis and management. Subsequently, based on parameters such as the average flow velocity and average cross-section of the feature zones, it compares the changes in flow velocity before and after the changes to accurately identify abnormal feature zones and momentum risks, providing crucial early warnings for river safety management.

Description

Technical Field

[0001] This invention relates to the field of river patrol technology, specifically a river patrol data intelligent analysis system based on big data. Background Technology

[0002] River patrol is an important measure to ensure the health of rivers and maintain the aquatic ecological environment. It covers a wide range of aspects and is of great significance to the stable development of river systems.

[0003] Application CN107918395B discloses a method and system for inspecting sewage outlets in urban rivers, including a waterborne mobile base station and a sewage outlet detection robot. The two can communicate and are equipped with a positioning system. The waterborne mobile base station can manage and control the sewage outlet detection robot and acquire its data. Through coordinated operation, the system can efficiently complete the search and location of sewage outlets in rivers and feed the data back to the user, resulting in high efficiency. The waterborne mobile base station includes a patrol vehicle equipped with a control center, a positioning module, and a base station power supply. The sewage outlet detection robot includes an underwater robot equipped with an obstacle avoidance system, a sewage outlet detection unit, a robot power supply, and a robot controller. This invention's urban river sewage outlet inspection system includes a sewage outlet detection robot capable of automatically patrolling underwater to detect the location of sewage outlets. This system is of great significance for river management.

[0004] Regarding the specific process of river patrol, traditional manual foot patrols can observe the river conditions in detail at close range, but the efficiency is low and it is suitable for patrolling small areas or key areas. Vehicle patrols are suitable for longer riverbanks and can quickly cover a large area. With the development of the times, unmanned boats are generally used to patrol rivers. However, during the patrol process, the patrol is simply carried out without assessing whether there are momentum risks in the corresponding river area based on the specific data collected. The original river patrol and handling methods still need to be improved. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a big data-based intelligent analysis system for river patrol data, which solves the problem of not being able to assess whether there is momentum risk in the corresponding river area based on the specific data of the patrol.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a big data-based intelligent analysis system for river patrol data, comprising:

[0007] The river data acquisition end uses unmanned vessels to acquire real-time acoustic detection data and water flow velocity in the river.

[0008] The river channel contour generation end generates a contour model of the corresponding river channel in real time based on the acquired acoustic detection data, and then transmits the generated complete river channel contour model to the river channel feature processing end. The construction method is as follows:

[0009] The acoustic detection data includes the depth and angle data associated with each different point. Based on the current location of the unmanned vessel, the location of the corresponding acoustic detection point can be confirmed. Based on the specific progress of real-time detection, the specific internal contour of the corresponding river channel is generated in real time, and the construction of a complete river channel contour model is completed.

[0010] In the river feature processing stage, the generated complete river contour model is contour confirmed. Based on the specific line lengths of the two side edge contours, the specific differences between the two side edge contours are confirmed. Then, based on the confirmed specific differences, the complete river contour model is divided into regions, making the complete river contour model equally divided into different feature areas. The specific method is as follows:

[0011] Construct a set of standard horizontal planes based on the location of the unmanned vessel. These standard horizontal planes are parallel to the water surface of the river. Then, directly confirm the outlines that intersect the standard horizontal planes with the complete river outline model. Record the confirmed outlines on both sides as the two side edge outlines.

[0012] The lengths of the contour lines of the two side edges are confirmed from the complete river channel contour model. The length of one side contour line is marked as Lz and the length of the other side contour line is marked as Ly. The verification ratio Bz is confirmed by using (Lz:Ly) = Bz. The model is divided equally from the initial position of the complete river channel contour model. The number of equal divisions is N, where N is a preset value.

[0013] During the equal division, based on the confirmed verification ratio Bz, the contours on both sides are divided into N unit contours. Then, starting from the initial position, the corresponding unit contours are cross-sectionally confirmed, and the complete river contour model is divided into several equal regions. The line lengths of the contours on both sides of each equal region are consistent.

[0014] Based on the successively identified equal-divided regions, the volume parameters associated with each equal-divided region within the complete river channel outline model are confirmed and calibrated as R. i Where i represents different equal-divided regions, starting from the first confirmed equal-divided region, the volume difference between adjacent equal-divided regions is confirmed sequentially, and the volume difference = |R| j -R j+1|, where j∈i, if the volume difference ≤ Y1, then the associated equal-divided region is labeled as the same feature region, where Y1 is a preset value. Multiple equal-divided regions belonging to the same feature region are integrated and the feature region is locked. Different same feature regions are integrated into different feature regions. The complete river channel outline model is divided into multiple different feature regions, and the different feature regions are transmitted to the flow velocity assessment processing terminal. If the volume difference > Y1, then no labeling is performed.

[0015] If a single equally divided region does not belong to the same characteristic region as its preceding and following equally divided regions, then this equally divided region belongs to a single characteristic region.

[0016] The velocity assessment processing unit, based on multiple feature zones divided within the complete river channel outline model, identifies the mean cross-section associated with each feature zone. Then, based on the associated flow velocity of each feature zone, it identifies the velocity change between the corresponding feature zone and the previous feature zone. Based on the identified velocity change characteristics, it assesses whether there is momentum risk in the corresponding feature zone. The specific method is as follows:

[0017] Based on the identified feature regions, the water flow velocities monitored within these feature regions at different locations are confirmed. Then, the average values ​​of several sets of water flow velocities are calculated to identify the average velocity associated with the corresponding feature region and denoted as L. q , where q represents different feature regions, and q = 1, 2, ..., n. When q is 1, it represents the first feature region, and when q is n, it represents the last feature region.

[0018] Next, confirm the specific line lengths of the edge contours on both sides of the feature area, select the minimum line length from the specific line lengths on both sides and denot it as C. q min, then confirm the volume parameter TZ of this feature region. q Using: TZ q ÷C q min = Jm q Lock the mean cross section Jm for this feature region q Its Jm q Represents area parameters;

[0019] Based on the direction of water flow, the first feature zone is selected from the complete river channel profile model. The cross-sectional flow rate of the first feature zone is confirmed by L1×C1min=JL1. Then, the mean velocity L2 and mean cross section Jm2 of the second feature zone following the first feature zone are confirmed. The standard velocity V2 is locked by JL1÷Jm2=V2. Then, the velocity difference CZ2 of the second feature zone is confirmed by |L2-V2|=CZ2. If CZ2>Y2, the second feature zone is marked as an abnormal feature zone, which means that there is momentum risk. Y2 is a preset value. If CZ2≤Y2, no marking is performed.

[0020] The average flow velocity L2 and average cross section Jm2 of the second characteristic zone are used to determine the corresponding cross section flow rate. Then, the cross section flow rate is used to analyze the relevant values ​​of the third characteristic zone to determine whether the third characteristic zone belongs to the abnormal characteristic zone. Similarly, based on the water flow direction, the relevant values ​​of the previous set of characteristic zones are used as a benchmark to determine whether the flow velocity difference of the next set of characteristic zones is abnormal. Abnormal characteristic zones are evaluated in turn.

[0021] Preferred options also include:

[0022] At the signal end, based on the calibrated abnormal feature area, a momentum risk signal for this abnormal feature area is generated and displayed for external personnel to view.

[0023] This invention provides an intelligent analysis system for river patrol data based on big data. Compared with existing technologies, it has the following advantages:

[0024] This invention uses a river feature processing terminal to divide the river contour model equally according to the difference in contour line length. By analyzing volume parameters, it locks the regions with the same features and divides different feature regions, simplifying the complex river contour into multiple regions with clear features, which facilitates targeted analysis and management.

[0025] Subsequently, based on parameters such as the mean flow velocity and mean cross section of the characteristic area, the changes in flow velocity in the characteristic area before and after are compared to accurately identify abnormal characteristic areas and momentum risks, providing key early warnings for river safety management. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0028] First embodiment

[0029] Please see Figure 1 This application provides a big data-based intelligent analysis system for river patrol data, including a river data acquisition end, a river contour generation end, a river feature processing end, a flow velocity assessment and processing end, and a signal end. The river data acquisition end, the river contour generation end, and the river feature processing end are electrically connected from the output node to the input node in sequence. The river data acquisition end and the river feature processing end are both electrically connected to the input node of the flow velocity assessment and processing end, and the flow velocity assessment and processing end is electrically connected to the input node of the signal end.

[0030] The river data acquisition end uses an unmanned surface vessel (USV) to acquire real-time acoustic detection data and water flow velocity of the river. The real-time acoustic detection data is then transmitted to the river contour generation end, and the acquired water flow velocity is transmitted to the flow velocity assessment and processing end. Specifically, the acoustic detection data and water flow velocity are acquired by the USV, which is equipped with an acoustic detector and a flow velocity sensor. The acoustic detector detects the contour features of the river in real time and generates detection data, while the flow velocity sensor detects the water flow velocity in the river in real time. The real-time detected water flow velocity and river detection data are then transmitted to the river contour generation end.

[0031] The river contour generation end generates a contour model of the corresponding river in real time based on the acquired acoustic detection data, and transmits the generated complete river contour model to the river feature processing end. Specifically, the acoustic detection data includes the depth and angle data associated with each different point. Based on the current location of the unmanned vessel, the location of the corresponding acoustic detection point can be confirmed. Based on the real-time detection process, the real-time associated acoustic detection data can be confirmed, and the specific internal contour of the corresponding river can be generated based on the real-time associated acoustic detection data. The specific internal contour can display the relevant state of the river, which is convenient for human verification, evaluation of the feature areas of different widths existing inside the river contour, and subsequent evaluation.

[0032] In the river feature processing stage, the generated complete river contour model is contour confirmed. Based on the specific line lengths of the two side edge contours, the specific differences between the two side edge contours are confirmed. Then, based on the confirmed specific differences, the complete river contour model is divided into regions, making the complete river contour model equally divided into different feature areas. Specifically, different feature areas may have different widths or varying widths, but within the corresponding feature areas, the numerical changes between their cross-sections are relatively consistent. Therefore, by using this evaluation and processing method, the specific changes of the corresponding feature areas can be confirmed and numerical analysis can be performed in a timely manner to identify the feature areas with different numerical conditions. The specific method for dividing the regions is as follows:

[0033] Construct a set of standard horizontal planes based on the location of the unmanned vessel. These standard horizontal planes are parallel to the water surface of the river. Then, directly confirm the outlines that intersect the standard horizontal planes with the complete river outline model. Record the confirmed outlines on both sides as the two side edge outlines.

[0034] The lengths of the contour lines on both sides of the complete river channel outline model are confirmed. The length of one side of the contour line is marked as Lz and the length of the other side of the contour line is marked as Ly. The verification ratio Bz is confirmed by using (Lz:Ly) = Bz. The model is divided equally from the initial position of the complete river channel outline model. The number of equal divisions is N. N is a preset value, which is determined by the relevant operators based on experience. N is generally above 1000. Its specific value is determined by the specific length of the corresponding river channel.

[0035] During the equal division, based on the confirmed verification ratio Bz, the two side edge contours are divided into N unit contours. Then, starting from the initial position, the corresponding unit contours are cross-sectionally confirmed, dividing the complete river channel contour model into several equal regions. The line lengths of the contours on both sides of each equal region are consistent (consistent means that the unit line lengths associated with one side edge contour of each equal region are consistent, and the unit line lengths on the other side edge contour are also consistent), ensuring that the line length characteristics of the contours on both sides of each equal region are consistent. If the contour line length of one side is calibrated... With Lz = 10, the length of the other side's contour line is set to Ly = 20. Each time the model is divided, the unit length of the division is 0.5 units. Starting from the initial position of the model, 0.5 units of edge line length are determined on one side of the contour line. The determined ratio is 0.5. Then, 1 unit of edge line length is determined on the other side of the contour line. By using this method of division, the model can be divided into several equally divided regions with the same edge feature length. This process can be repeated to facilitate the specific confirmation of the feature regions in the future.

[0036] Based on the successively identified equal-divided regions, the volume parameters associated with each equal-divided region within the complete river channel outline model are confirmed and calibrated as R. i Where i represents different equal-divided regions, starting from the first confirmed equal-divided region, the volume difference between adjacent equal-divided regions is confirmed sequentially, and the volume difference = |R| j -R j+1 |, where j∈i, if the volume difference ≤ Y1, then the associated equal-divided region is marked as the same feature region; if the volume difference > Y1, then no marking is performed, and Y1 is a preset value. Its specific value is determined by the operator based on experience. Multiple equal-divided regions belonging to the same feature region are integrated and the feature region is locked. Different regions with the same feature are integrated into different feature regions. The complete river contour model is divided into multiple different feature regions, and the different feature regions are transmitted to the flow velocity assessment and processing terminal.

[0037] If a single equally divided region does not belong to the same characteristic region as its preceding and following equally divided regions, then this equally divided region belongs to a single characteristic region.

[0038] Specifically, after the river model is confirmed, it is divided into multiple individual regions with relatively consistent edge contours based on the specific line lengths of the contours on both sides and the specific differences in the contour line lengths. After obtaining the specific region division, the specific differences between adjacent regions are evaluated based on the relative changes in the corresponding volume parameters. Based on the evaluation results, specific regions with relatively consistent internal spatial characteristics are locked. Based on the locked specific regions, the river model is divided equally, so that the corresponding river model is divided into multiple equally divided regions, and the corresponding equally divided regions can achieve the specific effect of equal division.

[0039] Second embodiment

[0040] In this embodiment, based on the different feature regions and the monitored flow velocity, it is determined whether there are any abnormalities in the flow velocity of the corresponding feature region, and based on the specific intelligent judgment results, the corresponding judgment signal is confirmed and displayed.

[0041] In the velocity assessment processing section, based on multiple feature zones divided within the complete river channel outline model, the mean cross section associated with each feature zone is identified. Then, based on the water flow velocity associated with each feature zone, the velocity change between the corresponding feature zone and the previous feature zone is identified. Based on the identified velocity change characteristics, the existence of momentum risk in the corresponding feature zone is assessed. The specific assessment method is as follows:

[0042] Based on the identified feature regions, the water flow velocities monitored within these feature regions at different locations are confirmed. Then, the average values ​​of several sets of water flow velocities are calculated to identify the average velocity associated with the corresponding feature region and denoted as L. q , where q represents different feature regions, and q = 1, 2, ..., n. When q is 1, it represents the first feature region, and when q is n, it represents the last feature region.

[0043] Next, confirm the specific line lengths of the edge contours on both sides of the feature area, select the minimum line length from the specific line lengths on both sides and denot it as C. q min, then confirm the volume parameter TZ of this feature region. q Using: TZ q ÷C q min = Jm q Lock the mean cross section Jm for this feature region q Its Jm q Represents area parameters;

[0044] Based on the direction of water flow, the first feature zone is selected from the complete river channel outline model. The cross-sectional flow rate of the first feature zone is confirmed by L1×C1min=JL1. Then, the mean flow velocity L2 and mean cross-sectional flow rate Jm2 of the second feature zone following the first feature zone are confirmed. The standard flow velocity V2 is locked by JL1÷Jm2=V2. Then, the velocity difference CZ2 of the second feature zone is confirmed by |L2-V2|=CZ2. If CZ2>Y2, the second feature zone is marked as an abnormal feature zone, which means that there is momentum risk. Y2 is a preset value, and its specific value is determined by the operator based on experience. Otherwise, no calibration is performed.

[0045] The average flow velocity L2 and average cross section Jm2 of the second characteristic zone are used to determine the corresponding cross section flow rate. Then, the cross section flow rate is used to analyze the relevant values ​​of the third characteristic zone to determine whether the third characteristic zone belongs to the abnormal characteristic zone. Similarly, based on the water flow direction, the relevant values ​​of the previous set of characteristic zones are used as a benchmark to determine whether the flow velocity difference of the next set of characteristic zones is abnormal. Abnormal characteristic zones are evaluated in turn.

[0046] In the signaling section, a momentum risk signal is generated based on the identified abnormal feature area. The generated momentum risk signal is then displayed for external personnel to view. Based on this momentum risk signal, external personnel can conduct on-site surveys to check whether there is a risk of dam breach in this feature area.

[0047] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0048] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention 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 the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A big data-based intelligent analysis system for river patrol data, characterized in that: include: The river data acquisition end uses unmanned vessels to acquire real-time acoustic detection data and water flow velocity in the river. The river contour generation end generates a contour model of the corresponding river in real time based on the acquired acoustic detection data, and transmits the generated complete river contour model to the river feature processing end. In the river feature processing stage, the generated complete river contour model is contour confirmed. Based on the specific line lengths of the two side edge contours, the specific differences between the two side edge contours are confirmed. Then, based on the confirmed specific differences, the complete river contour model is divided into regions, making the complete river contour model equally divided into different feature areas. The specific method is as follows: Construct a set of standard horizontal planes based on the location of the unmanned vessel. These standard horizontal planes are parallel to the water surface of the river. Then, directly confirm the outlines that intersect the standard horizontal planes with the complete river outline model. Record the confirmed outlines on both sides as the two side edge outlines. The lengths of the contour lines of the two side edges are confirmed from the complete river channel contour model. The length of one side contour line is marked as Lz and the length of the other side contour line is marked as Ly. The verification ratio Bz is confirmed by using (Lz:Ly) = Bz. The model is divided equally from the initial position of the complete river channel contour model. The number of equal divisions is N, and N is a preset value. During the equal division, based on the confirmed verification ratio Bz, the contours on both sides are divided into N unit contours. Then, starting from the initial position, the corresponding unit contours are cross-sectionally confirmed, and the complete river contour model is divided into several equal regions. The line lengths of the contours on both sides of each equal region are consistent. Based on the successively identified equal-divided regions, the volume parameters associated with each equal-divided region within the complete river channel outline model are confirmed and calibrated as R. i Where i represents different equal-divided regions, starting from the first confirmed equal-divided region, the volume difference between adjacent equal-divided regions is confirmed sequentially, and the volume difference = |R| j -R j+1 |, where j∈i, if the volume difference is ≤Y1, then the associated equal-divided region is marked as the same feature region, where Y1 is a preset value. Multiple equal-divided regions belonging to the same feature region are integrated and locked into the feature region. Different same feature regions are integrated into different feature regions. The complete river contour model is divided into multiple different feature regions, and the different feature regions are transmitted to the flow velocity assessment processing terminal. If a single equally divided region does not belong to the same characteristic region as its preceding and following equally divided regions, then this equally divided region belongs to a single characteristic region. The velocity assessment processing unit, based on multiple feature zones divided within the complete river channel outline model, identifies the mean cross-section associated with each feature zone. Then, based on the associated flow velocity of each feature zone, it identifies the velocity change between the corresponding feature zone and the previous feature zone. Based on the identified velocity change characteristics, it assesses whether there is momentum risk in the corresponding feature zone. The specific method is as follows: Based on the identified feature regions, the water flow velocities monitored within these feature regions at different locations are confirmed. Then, the average values ​​of several sets of water flow velocities are calculated to identify the average velocity associated with the corresponding feature region and denoted as L. q , where q represents different feature regions, and q = 1, 2, ..., n. When q is 1, it represents the first feature region, and when q is n, it represents the last feature region. Next, confirm the specific line lengths of the edge contours on both sides of the feature area, select the minimum line length from the specific line lengths on both sides and denot it as C. q min, then confirm the volume parameter TZ of this feature region. q Using: TZ q ÷C q min=Jm q Lock the mean cross section Jm for this feature region q Its Jm q Represents area parameters; Based on the direction of water flow, the first feature zone is selected from the complete river channel outline model. The cross-sectional flow rate of the first feature zone is confirmed by L1×Jm1=JL1. Then, the mean velocity L2 and mean cross section Jm2 of the second feature zone following the first feature zone are confirmed. The standard velocity V2 is locked by JL1÷Jm2=V2. Then, the velocity difference CZ2 of the second feature zone is confirmed by |L2-V2|=CZ2. If CZ2>Y2, the second feature zone is marked as an abnormal feature zone, which means that there is momentum risk. Y2 is a preset value. The average flow velocity L2 and average cross section Jm2 of the second characteristic zone are used to determine the corresponding cross section flow rate. Then, the cross section flow rate is used to analyze the relevant values ​​of the third characteristic zone to determine whether the third characteristic zone belongs to the abnormal characteristic zone. Similarly, based on the water flow direction, the relevant values ​​of the previous set of characteristic zones are used as a benchmark to determine whether the flow velocity difference of the next set of characteristic zones is abnormal. Abnormal characteristic zones are evaluated in turn.

2. The intelligent analysis system for river patrol data based on big data as described in claim 1, characterized in that, The method for constructing the contour model at the river contour generation end is as follows: The acoustic detection data includes depth and angle data associated with each different point. Based on the current location of the unmanned vessel, the location of the corresponding acoustic detection point can be confirmed. Based on the real-time detection process, the specific internal contour of the corresponding river channel is generated in real time, and the construction of a complete river channel contour model is completed.

3. The intelligent analysis system for river patrol data based on big data as described in claim 1, characterized in that, If the volume difference is greater than Y1, no calibration is performed.

4. The intelligent analysis system for river patrol data based on big data as described in claim 1, characterized in that, If CZ2≤Y2, then no calibration is performed.

5. The intelligent analysis system for river patrol data based on big data as described in claim 4, characterized in that, Also includes: At the signal end, based on the calibrated abnormal feature area, a momentum risk signal for this abnormal feature area is generated and displayed for external personnel to view.

Images