Intelligent river flow monitoring method and system based on multi-source data fusion

Abstract

The application discloses a river flow intelligent monitoring method and system based on multi-source data fusion, relates to the technical field of river flow monitoring, and comprises the following steps: collecting multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density in a target river basin, and configuring a parameter judgment benchmark; connecting a flow monitoring device; evaluating the feasibility of ADCP sailing type flow measurement based on the parameter judgment benchmark; when the effective measurement probability of the ADCP is lower than a preset threshold, synchronously adjusting the sampling frequency and the channel coverage range of the flow monitoring device; and performing coordinate correction on the ADCP sailing section data and the discrete point data of the flow monitoring device under the parameter judgment benchmark to generate a flow monitoring report with a confidence rating. The application solves the technical problem that the existing technology cannot comprehensively obtain river flow information, which leads to insufficient accuracy and reliability of flow monitoring in a complex river environment, and achieves the technical effect of improving the accuracy and reliability of river flow monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of river flow monitoring, and particularly relates to a multi-source data fusion river flow intelligent monitoring method and system. BACKGROUND

[0002] River flow monitoring is an important measure for water resource management, flood control and disaster reduction, and ecological environment protection, and its accuracy and timeliness are crucial. Traditional river flow monitoring cannot meet the increasing accuracy requirements of river flow monitoring in complex and variable river environments. For example, the flow velocity meter method relies on limited point flow velocity measurement and cannot fully reflect the spatial distribution difference of river section flow velocity. In irregular river morphology and strong water flow turbulence areas, the measurement result deviation is significant. The float method can track the water flow trajectory, but is greatly affected by floating objects and wind direction, and cannot accurately obtain key parameters such as water depth and flow velocity gradient, resulting in large flow calculation error. This further affects the accuracy and reliability of river flow monitoring.

[0003] Therefore, in the related art, there is a technical problem that it is difficult to comprehensively obtain river flow information, resulting in insufficient accuracy and reliability of flow monitoring in complex river environments. SUMMARY

[0004] The present application provides a multi-source data fusion river flow intelligent monitoring method and system, which solves the technical problem that it is difficult to comprehensively obtain river flow information in the prior art, resulting in insufficient accuracy and reliability of flow monitoring in complex river environments, and achieves the technical effect of improving the accuracy and reliability of river flow monitoring.

[0005] The present application provides a multi-source data fusion river flow intelligent monitoring method, which comprises: collecting multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density in a target river basin, and configuring a parameter judgment benchmark; connecting a flow monitoring device, evaluating the feasibility of ADCP walk-through flow measurement based on the parameter judgment benchmark, the flow monitoring device comprising a rotor flow velocity meter and a Doppler profiler; when the effective measurement probability of ADCP is lower than a preset threshold, synchronously adjusting the sampling frequency and channel coverage range of the flow monitoring device, performing coordinate correction on ADCP walk-through section data and discrete point data of the flow monitoring device under the parameter judgment benchmark, and generating a flow monitoring report with a confidence rating.

[0006] In a possible implementation manner, the multi-source data fusion river flow intelligent monitoring method further performs the following processing: using a sonar detection device to obtain river bottom morphology information of the target river basin; uploading the river bottom morphology information to a cloud computing center, and filtering the multi-source river characteristic parameters based on the river bottom morphology information.

[0007] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: based on the Doppler profiler in the flow monitoring device, an array of Doppler profilers is deployed at equal intervals along the water flow direction, and the first technical index corresponding to the array of Doppler profilers includes a vertical layer number and a layer thickness resolution; based on the rotor current meter in the flow monitoring device, a fixed-point measurement point is arranged at a key monitoring section, and the second technical index corresponding to the fixed-point measurement point includes a measurement point density and a flow speed measurement accuracy; and the first technical index and the second technical index are jointly configured according to the river water depth and the flow speed gradient in the multi-source river characteristic parameter.

[0008] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: the ADCP track and the sampling point of the flow monitoring device are spatially aligned, the communication protocol of the flow monitoring device is synchronously adjusted, and the data transmission time delay is determined; the time synchronization accuracy is obtained through the data transmission time delay; and the data resampling mechanism of the flow monitoring device is configured with the time synchronization accuracy according to the river water depth and the floating object density in the multi-source river characteristic parameter.

[0009] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: a multi-source sensor network is deployed in a target river basin, and the multi-source sensor network is used to collect the multi-source river characteristic parameter; a river section flow speed distribution map is generated based on the multi-source river characteristic parameter, and the ADCP track and the sampling point of the flow monitoring device are spatially aligned with the river section flow speed distribution map and GIS data.

[0010] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: when the floating object density fluctuation exceeds a preset fluctuation interval and the data proportion under the data resampling mechanism is greater than a proportion threshold, a cross-validation mechanism is triggered; the confidence interval is determined by using the cross-validation mechanism, and the confidence rating is updated by using the confidence interval.

[0011] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: in the multi-source sensor network, a floating object tracking coordinate is located, and the flow monitoring device and the sonar detection device cooperatively work at the floating object tracking coordinate; floating object tracking data are collected through the floating object tracking coordinate, the influence of the floating object density fluctuation on the river flow is analyzed, and the preset fluctuation interval is configured.

[0012] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: when the floating object density fluctuation exceeds a preset fluctuation range, a floating object sheltering avoidance reminder is sent, and the floating object sheltering avoidance reminder is bound to floating object tracking coordinates and a floating object dense area mark.

[0013] In a possible implementation, the river flow intelligent monitoring method based on multi-source data fusion further performs the following processing: according to the floating object tracking coordinates, an edge computing node is deployed, the edge computing node is in communication connection with a cloud computing center; the edge computing node receives the floating object tracking coordinates bound by the floating object sheltering avoidance reminder, predicts a river influence range under a floating object gathering trend, and performs elastic expansion on a floating object dense area.

[0014] The application further provides a river flow intelligent monitoring system based on multi-source data fusion, the system comprising: a river characteristic parameter acquisition module, configured to acquire multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density in a target river basin, and configure a parameter judgment benchmark; a parameter judgment evaluation module, configured to connect a flow monitoring device, evaluate the feasibility of ADCP walk-through flow measurement based on the parameter judgment benchmark, the flow monitoring device comprising a rotor flowmeter and a Doppler profiler; and a flow monitoring report generation module, configured to, when the ADCP effective measurement probability is lower than a preset threshold, synchronously adjust the sampling frequency and channel coverage range of the flow monitoring device, perform coordinate correction on ADCP walk-through cross-section data under the parameter judgment benchmark and discrete point data of the flow monitoring device, and generate a flow monitoring report with a confidence level.

[0015] The river flow intelligent monitoring method and system based on multi-source data fusion are used to acquire multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density in a target river basin, and configure a parameter judgment benchmark; connect a flow monitoring device, evaluate the feasibility of ADCP walk-through flow measurement based on the parameter judgment benchmark; when the ADCP effective measurement probability is lower than a preset threshold, synchronously adjust the sampling frequency and channel coverage range of the flow monitoring device, perform coordinate correction on ADCP walk-through cross-section data under the parameter judgment benchmark and discrete point data of the flow monitoring device, and generate a flow monitoring report with a confidence level. The technical problems that it is difficult to comprehensively acquire river flow information in the prior art, and the flow monitoring accuracy and reliability are insufficient in a complex river environment are solved, and the technical effect of improving the accuracy and reliability of river flow monitoring is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. In the present application, a flow chart is used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously as needed. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A flow chart of a river flow intelligent monitoring method of multi-source data fusion provided by the embodiments of the present application.

[0018] Figure 2 A structure diagram of a river flow intelligent monitoring system of multi-source data fusion provided by the embodiments of the present application.

[0019] Legend: river feature parameter acquisition module 10, parameter determination and evaluation module 20, flow monitoring report generation module 30. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application more clear, the following will further describe the present application in combination with the drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present application.

[0022] In the following description, "some embodiments" are described, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict. The term "first\second" is only to distinguish similar objects, and does not represent a specific order of the object. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art in the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiment of the present application provides a river flow intelligent monitoring method based on multi-source data fusion, as shown in the figure, the method comprises the following steps: Figure 1

[0024] Step S100, collecting multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density in the target river basin, and configuring parameter judgment criteria.

[0025] Preferably, the multi-source river characteristic parameters of the target river basin include river water depth, flow velocity gradient and floating object density, specifically, the river water depth refers to the vertical distance from the water surface to the river bottom, the water depth data of different positions are measured by using a depth finder and the like, so that the longitudinal profile shape of the river and the water depth change condition of different regions are known, and the river water carrying capacity, water flow structure and cross section area in the flow calculation are analyzed; the flow velocity gradient refers to the change rate of the flow velocity with the distance in the direction perpendicular to the water flow, the acoustic Doppler current profiler (ADCP) is used to measure the water flow velocity at different depths and positions, and then the flow velocity gradient is calculated to reflect the vertical structure and turbulence characteristics of the water flow, and the river flow and the energy transmission of the water flow are accurately calculated; the floating object density refers to the number of floating objects in a unit volume of water, the floating objects in the target region are statistically analyzed by visual observation or floating object monitoring equipment based on image recognition, and the floating object density information is obtained, and the pollution condition of the river and the transport capacity of the water flow to the floating objects are known, and the interference of the floating objects on the measuring equipment is also excluded in the river flow monitoring.

[0026] Preferably, the parameter judgment criteria are configured according to the multi-source river characteristic parameters, specifically, the suitable water depth range of different regions is set according to the historical data of the target river, the experience value of similar rivers and the function of the river (such as navigation requirement, irrigation demand and the like); the reasonable flow velocity gradient range is determined according to the stability of the water flow and the historical data of the target river, if the flow velocity gradient exceeds the normal range, it means that the water flow has abnormal turbulence, which is easy to cause river erosion, river bank collapse and the like; the reasonable range of the floating object density is determined according to the water quality standard of the target river, when the floating object density exceeds the set limit value, it indicates that the river is seriously polluted, and cleaning needs to be organized in time. By setting reasonable judgment standards or threshold values (namely, configuring parameter judgment criteria) for each parameter, the condition of the river is evaluated and judged, so that the condition of the target river basin is comprehensively and accurately known.

[0027] Further, step S100 further comprises the following steps: step S110, acquiring the river bottom morphology information of the target river basin by using a sonar detection device; and step S120, uploading the river bottom morphology information to a cloud computing center, and filtering the multi-source river characteristic parameters through the river bottom morphology information. ​

[0028] Preferably, the sonar detection device is a monitoring device that uses the characteristics of sound wave propagation in water to detect underwater objects and terrain. Specifically, in the target river basin, the sonar device emits sound wave signals and then receives the sound waves reflected from the river bottom. According to the propagation time and speed of the sound waves, the depth information of different positions on the river bottom is calculated, and the river bottom morphology information is determined, which can accurately present the terrain undulation, concave-convex change, obstacle distribution, etc. of the river bottom. The river bottom morphology information is uploaded to the cloud computing center. After the cloud computing center receives the river bottom morphology information obtained by the sonar detection device, it filters the multi-source river characteristic parameters (such as river depth, flow velocity gradient, and floating object density) to remove abnormal data points in the multi-source river characteristic parameters.

[0029] Preferably, due to the complexity of the measurement environment and various interference factors, the collected multi-source river characteristic parameters may contain abnormal data points. For example, in areas with protrusions or depressions on the river bottom, water depth measurement may be affected and deviate, and flow velocity measurement may also produce abnormal values due to local water flow turbulence. By comparing the multi-source river characteristic parameters with the river bottom morphology information, special morphology information of the river bottom such as shoals, deep pools, reefs, and steep slopes is identified, which will affect the water flow and cause abnormalities in the multi-source river characteristic parameters. For example, in the shoal area, the water flow speed may increase and the water depth measurement value may be relatively small; in the deep pool area, the water flow speed may slow down and there may be eddies affecting the measurement of the flow velocity gradient. Then, according to the special terrain information of the river bottom, abnormal data in the river characteristic parameters is identified and filtered, for example, for river depth data, if the measured water depth at a certain position is significantly different from the normal water depth calculated based on the river bottom morphology information, and after excluding measurement errors, the data point is judged as an abnormal point and is removed; for flow velocity gradient data, if the flow velocity gradient near the special terrain appears a sudden change that does not conform to the laws of water flow dynamics, it is considered as abnormal data for filtering; for floating object density data, if the floating object density in a certain area is abnormally high or low and does not conform to the water flow convergence or dispersion reflected by the river bottom morphology, it is marked as abnormal data and corrected.

[0030] Further, step S100 further includes step S130 of deploying a multi-source sensor network in the target river basin, the multi-source sensor network being used to collect the multi-source river characteristic parameters; and step S140 of generating a river cross-section flow velocity distribution map based on the multi-source river characteristic parameters, and spatially aligning the river cross-section flow velocity distribution map with GIS data, ADCP track and sampling points of the flow monitoring device.

[0031] Preferably, a plurality of types of sensors are arranged in the target river basin to form a multi-source sensor network to comprehensively collect river flow characteristic parameters, including but not limited to water depth, flow velocity, water quality, flow rate, etc. of the river, and then the flow velocity in the multi-source river characteristic parameters is used to analyze and calculate the flow velocity of a certain section of the river and display it in a graphical manner to form a river section flow velocity distribution map, which can intuitively present the flow velocity and distribution of different positions on the river section, such as showing that the flow velocity is faster in the center of the river and slower near the shore, etc. Then, the river section flow velocity distribution map and GIS geographic information data (geographic position, topography, coordinates, etc. of the river) are used to compare and match the ADCP track and the flow velocity data of the sampling points of the flow monitoring equipment to determine the corresponding relationship of the flow velocity distribution, and then the geographic coordinates of the ADCP track and the sampling points of the flow monitoring equipment are matched and calibrated with the coordinates of the river in the GIS data to ensure that they correspond to the actual position of the river in space, so that the measurement data of the river basin is more accurate.

[0032] In step S200, the flow monitoring equipment is connected to evaluate the feasibility of ADCP walk-by flow measurement based on the parameter determination criteria, and the flow monitoring equipment includes a rotor flow meter and a Doppler profiler.

[0033] Preferably, ADCP (Acoustic Doppler Current Profiler) walk-by flow measurement is a river flow measurement method that measures the water flow velocity profile by transmitting and receiving acoustic signals, and then calculates the river flow. When ADCP is used for flow measurement, the flow monitoring equipment including a rotor flow meter and a Doppler profiler is connected, wherein the rotor flow meter measures the water flow velocity by the rotation of the rotor in the water flow, which is suitable for various water flow conditions, especially in the case of relatively stable water flow and low flow velocity, and can provide more accurate measurement results; the Doppler profiler measures the water flow velocity profile using the acoustic Doppler effect, that is, the Doppler profiler transmits acoustic waves, and the acoustic waves are scattered when they encounter scattering bodies (such as suspended particles, plankton, etc.) in the water. A part of the scattered waves is received by the instrument. Since the scattering bodies move with the water flow, according to the Doppler effect, the frequency of the received wave will be different from the frequency of the transmitted wave. By measuring the frequency difference, the movement speed of the scattering body is calculated, and then the velocity profile of the water flow is obtained.

[0034] Preferably, the feasibility is evaluated according to the parameter judgment criteria, that is, the collected river channel characteristic parameters such as water depth, flow velocity gradient, and floating object density are compared and analyzed with the corresponding parameter judgment criteria. For example, if the water depth of the river channel changes too drastically, there are some extremely shallow areas, which may cause the transducer of the ADCP to fail to work normally or the measurement accuracy to be seriously affected. If the water depth is too deep and exceeds the effective measurement range of the ADCP, the measurement result will also be less accurate. A large flow velocity gradient may cause a large error in the ADCP measured water flow velocity profile. The ADCP measures the flow velocity based on the acoustic principle and assumption. When the flow velocity gradient exceeds the adaptive range, the measurement result may be distorted. A large amount of floating objects may interfere with the acoustic signal propagation of the ADCP, affecting the measurement accuracy. The floating objects may reflect or scatter the acoustic waves emitted by the ADCP, making the received signal complex and unstable, thereby causing the measurement result to deviate, and even the effective flow velocity data may not be normally obtained.

[0035] Further, step S200 further includes step S210 of deploying a Doppler profiler array along the water flow direction at equal intervals based on the Doppler profiler in the flow monitoring device, the first technical index corresponding to the Doppler profiler array including a vertical layer number and a layer thickness resolution; step S220 of setting a fixed-point measurement point at a key monitoring section based on a rotor flow velocity meter in the flow monitoring device, the second technical index corresponding to the fixed-point measurement point including a measurement point density and a flow velocity measurement accuracy; and step S230 of jointly configuring the first technical index and the second technical index according to the river channel water depth and the flow velocity gradient in the multi-source river channel characteristic parameters.

[0036] Preferably, a plurality of Doppler profilers are arranged along the water flow direction at equal interval distances to obtain a Doppler profiler array, so as to realize comprehensive monitoring of the water flow condition in the target river channel region. The first technical index corresponding to the Doppler profiler array includes a vertical layer number and a layer thickness resolution. The vertical layer number refers to the number of layers in which the Doppler profiler measures the water flow velocity in the vertical direction. For example, the entire water depth range from the water surface to the water bottom is divided into a plurality of different layers, and the water flow velocity in each layer can be independently measured. The more the vertical layer number, the more detailed the water flow velocity change in the vertical direction can be obtained. The layer thickness resolution refers to the thickness of each vertical layer, which determines the accuracy of the water flow velocity measurement in the vertical direction. The higher the layer thickness resolution, the smaller the thickness of each layer, and the more accurate the water flow velocity measurement. For example, the layer thickness resolution is 0.1 meters, which means that the thickness of each measurement layer is 0.1 meters, and the small change of the water flow velocity in the vertical direction can be captured more detailedly.

[0037] Preferably, according to the second technical index (including the measurement point density, the flow velocity measurement accuracy), the fixed measurement points are arranged at the key monitoring section of the target river basin and the rotor flow velocity meters are arranged, which are used to measure the water flow velocity, wherein the measurement point density refers to the number of the rotor flow velocity meter measurement points arranged per unit area or per unit length at the key monitoring section, and the measurement point density determines the detailed degree of the water flow velocity distribution measurement of the section, and the higher the measurement point density is, the more accurate the water flow velocity information of different positions on the section is obtained; the flow velocity measurement accuracy refers to the accuracy degree of the rotor flow velocity meter when measuring the water flow velocity, which is usually represented by the error range between the measured value and the true value, and the higher the flow velocity measurement accuracy is, the more accurately the instrument can measure the true velocity of the water flow. According to the river depth and the flow velocity gradient, the first technical index (the vertical layer number, the layer thickness resolution) and the second technical index (the measurement point density, the flow velocity measurement accuracy) are jointly configured, that is, adjusted according to the actual situation of the river, so that the flow monitoring equipment can better adapt to the water flow conditions of different rivers, improve the accuracy and reliability of the flow measurement, and achieve the best flow monitoring effect.

[0038] Further, the step S200 further includes the following steps: S240, spatially aligning the ADCP walking track with the sampling points of the flow monitoring equipment, synchronously adjusting the communication protocol of the flow monitoring equipment, and determining the data transmission delay; S250, acquiring the time synchronization accuracy through the data transmission delay; S260, configuring the data resampling mechanism of the flow monitoring equipment according to the river depth and the floating object density in the multi-source river characteristic parameters and the time synchronization accuracy.

[0039] Preferably, the ADCP (acoustic Doppler current profiler) measures the water flow information along a certain track during walking, and the ADCP walking track is spatially aligned with the sampling points of the flow monitoring equipment, that is, the water flow information measured by the two is accurately corresponding in the spatial position, such as making the flow velocity data measured by the ADCP corresponding to the data of the sampling points of the flow monitoring equipment at the same position through the geographic positioning information; then the communication protocol of the flow monitoring equipment is synchronously adjusted, so that the flow monitoring equipment can communicate data in the same way, ensuring the accuracy and stability of data transmission, and measuring the time required for data transmission between the flow monitoring equipment, determining the time delay between data sending and data receiving, that is, the data transmission delay.

[0040] Preferably, according to the determined data transmission delay, the time synchronization accuracy, i.e. the time accuracy and consistency of the measured data, is obtained, and then the data supplement mechanism of the flow monitoring device is configured according to the river depth and the density of floating objects in the multi-source river channel feature parameters. For example, the deeper the river depth, the more difficult it is to measure the data, and data loss or low accuracy may occur. According to the time synchronization accuracy, more frequent data supplement is performed to ensure that complete and accurate flow information is obtained. When the density of floating objects is high, it will interfere with the measurement of the flow monitoring device, resulting in a decrease in data quality or data loss. According to the time synchronization accuracy and the specific situation of the floating objects, the data supplement and the frequency of the data supplement are adjusted to ensure that the flow monitoring device can obtain high-quality flow data and improve the accuracy and reliability of flow measurement.

[0041] Step S300, when the ADCP effective measurement probability is lower than the preset threshold, synchronously adjusting the sampling frequency and the channel coverage range of the flow monitoring device, performing coordinate correction on the ADCP walking section data and the discrete point data of the flow monitoring device under the parameter determination reference, and generating a flow monitoring report with a confidence rating.

[0042] Preferably, the preset threshold is a standard probability value set in advance, which is used to judge the effectiveness of ADCP walking flow measurement. Specifically, according to the parameter determination reference (such as river depth, flow velocity gradient, floating object density and other factors), the feasibility of ADCP (acoustic Doppler current profiler) walking flow measurement under the current river conditions is evaluated, i.e. the possibility of accurately measuring the flow, and then the effective measurement probability is obtained. If the effective measurement probability of ADCP is lower than the preset threshold, it means that the flow measurement task cannot be reliably completed in the current river environment; then the sampling frequency of the flow monitoring device is adjusted to obtain more accurate flow information; at the same time, the channel coverage range (the range of river areas that can be measured by the flow monitoring device) is adjusted to ensure that the flow of the entire river can be more comprehensively monitored.

[0043] Preferably, the ADCP measures and records the flow data of different positions of the river section during the navigation process to form the navigation section data, the flow monitoring equipment (such as a rotor current meter) measures at fixed discrete points to obtain discrete point data, and the two kinds of data are coordinate corrected to accurately correspond to the fusion of the ADCP navigation section data and the discrete point data of the flow monitoring equipment, including unifying the coordinates of the two kinds of data, and using geographic positioning information (such as GPS coordinates) to calibrate the data measured by different equipment in the spatial position. Then, the river flow is comprehensively analyzed in combination with the multi-source river channel characteristic parameters, and the confidence level of the flow analysis result is rated based on the accuracy, reliability of the data and the performance of the measuring equipment, wherein the confidence level indicates the credibility of the flow measurement result, for example, different levels such as high, medium and low can be used, if the data quality is high, the measuring equipment performance is stable and has been fully calibrated and verified, the confidence level of the flow analysis result is high, and vice versa, if the data has uncertainty or the measuring equipment has deficiencies in some aspects, the confidence level is low; and then a flow monitoring report is generated to ensure the monitoring accuracy and reliability.

[0044] Further, step S300 further includes step S310 of triggering a cross-validation mechanism when the floating object density fluctuation exceeds the preset fluctuation interval and the data proportion under the data supplement mechanism is greater than the proportion threshold; and step S320 of determining a confidence interval using the cross-validation mechanism and updating the confidence level using the confidence interval.

[0045] Preferably, the preset fluctuation interval is configured according to historical data and river characteristics to measure the normal change range of the floating object density, when the actually monitored floating object density fluctuation exceeds the preset interval, it indicates that the floating object in the river has an abnormal change, and the data amount obtained by the data supplement mechanism accounts for more than the proportion threshold in the total data amount, indicating that the data supplement is relatively frequent, that is, the reliability of the data has a problem; when the two conditions are met at the same time, the cross-validation mechanism is triggered, specifically, a plurality of flow monitoring methods or monitoring data are compared and verified, for example, ADCP measurement data is compared and analyzed with flow monitoring equipment (such as flow meter measurement data), or related data such as water level and slope of the river are combined to indirectly verify the accuracy of the flow data; a confidence interval is calculated through cross-validation, indicating that the true value may exist within a certain confidence interval; finally, the confidence level is updated according to the confidence interval, if the newly calculated confidence interval is narrow, it indicates that the data accuracy is high, and the confidence level is correspondingly improved, indicating that the flow monitoring data is more informative; if the confidence interval is wide, it indicates that the data has large uncertainty, and the confidence level is reduced, thereby making the confidence level in the flow monitoring report more accurate and reliable.

[0046] Further, step S310 further comprises step S311, locating the floating object tracking coordinates in the multi-source sensor network, the flow monitoring device and the sonar detection device work cooperatively at the floating object tracking coordinates; step S312, collecting floating object tracking data through the floating object tracking coordinates, analyzing the influence of floating object density fluctuation on river flow, and configuring a preset fluctuation range.

[0047] Preferably, in the multi-source sensor network, a plurality of sensors (such as cameras, radars, etc.) are used to locate the position of the floating object in the river channel and express it in the form of coordinates, i.e. floating object tracking coordinates. Through the floating object tracking coordinates, the moving track of the floating object in the river channel can be tracked in real time. Then the flow monitoring device and the sonar detection device work cooperatively according to the coordinate information to obtain more comprehensive floating object and river flow information. At the same time, floating object tracking data is collected through the floating object tracking coordinates, and the collected floating object tracking data and the water flow data obtained by the flow monitoring device are used to analyze the influence of the change of the floating object density on the river flow, for example, to study the influence degree of the increase or decrease of the floating object density on the water flow speed, flow direction, flow rate, etc., and whether it will cause the disturbance of the water flow, the local flow rate change, etc. Finally, according to the analysis result of the relationship between the floating object density fluctuation and the river flow, combined with the historical data and the actual situation of the river channel, a preset fluctuation range of the floating object density is set, which represents the range in which the floating object density should be in the river channel under normal circumstances. If the floating object density exceeds the preset fluctuation range, it means that the water flow state of the river channel is greatly affected, or there are some abnormal situations, so as to find out the possible problems in the river channel in time.

[0048] Further, step S312 further comprises issuing a floating object shielding avoidance reminder when the floating object density fluctuation exceeds the preset fluctuation range, the floating object shielding avoidance reminder being bound to the floating object tracking coordinates and the floating object dense area mark.

[0049] Preferably, if the monitored floating object density exceeds the preset fluctuation range, it means that the number or distribution of the floating object in the river channel changes abnormally, which may affect the related monitoring equipment or the operation of the river channel, and then a floating object shielding avoidance reminder is issued. The specific position information of the floating object is included in the reminder so as to find the accurate location of the floating object. Further, the area where the floating object is concentrated is marked to quickly identify which area the floating object is more concentrated, which may have greater impact on the river flow, monitoring equipment, etc., so that targeted measures can be taken, such as preferentially cleaning or strengthening the monitoring of these areas, to ensure the normal operation of the river channel.

[0050] Further, step S312 further comprises step A, deploying an edge computing node according to the floating object tracking coordinates, the edge computing node being in communication connection with a cloud computing center; and step B, the edge computing node receiving the floating object tracking coordinates bound in the floating object sheltering avoidance reminder, predicting the river impact range under the floating object gathering trend, and performing elastic expansion on the floating object dense area.

[0051] Preferably, the edge computing node is deployed according to the floating object tracking coordinates for data processing, to improve the response speed and be in communication connection with the cloud computing center. The edge computing node can upload the processed data to the cloud computing center for storage management, and can also receive the instruction information sent by the cloud computing center, to realize the collaborative work of the two. After receiving the floating object tracking coordinates bound in the floating object sheltering avoidance reminder, the edge computing node analyzes and predicts the gathering trend of the floating objects, for example, considering the water flow speed, wind direction, etc., to speculate the possible moving direction and gathering area of the floating objects in a future period of time, and then determine the range of the river that may be affected by the gathering of the floating objects, including the influence on the water flow speed, water quality, channel traffic, etc. Finally, according to the prediction result, the floating object dense area is elastically expanded, that is, according to the gathering trend and possible diffusion range of the floating objects, the area is appropriately expanded.

[0052] In the foregoing, with reference to Figure 1 The multi-source data fusion river flow intelligent monitoring method according to the embodiments of the present application is described in detail. Next, with reference to Figure 2 The multi-source data fusion river flow intelligent monitoring system according to the embodiments of the present application is described.

[0053] The multi-source data fusion river flow intelligent monitoring system according to the embodiments of the present application is used to solve the technical problem that it is difficult to comprehensively obtain river flow information in the prior art, resulting in insufficient accuracy and reliability of flow monitoring in complex river environments, and achieves the technical effect of improving the accuracy and reliability of river flow monitoring. As shown in Figure 2 The multi-source data fusion river flow intelligent monitoring system comprises a river feature parameter acquisition module 10, a parameter judgment and evaluation module 20, and a flow monitoring report generation module 30.

[0054] The river feature parameter acquisition module 10 is configured to acquire multi-source river feature parameters including river depth, flow velocity gradient and floating object density in the target river basin, and configure a parameter determination benchmark; the parameter determination and evaluation module 20 is configured to connect a flow monitoring device to evaluate the feasibility of ADCP walk-through flow measurement based on the parameter determination benchmark, the flow monitoring device including a rotor flowmeter and a Doppler profiler; and the flow monitoring report generation module 30 is configured to, when the effective ADCP measurement probability is lower than a preset threshold, synchronously adjust the sampling frequency and channel coverage range of the flow monitoring device, perform coordinate correction on ADCP walk-through cross-section data and discrete point data of the flow monitoring device under the parameter determination benchmark, and generate a flow monitoring report with a confidence rating.

[0055] In the following, the specific configuration of the river feature parameter acquisition module 10 will be described in detail. The river feature parameter acquisition module 10 further includes: using a sonar detection device to obtain river bottom morphology information of the target river basin; and uploading the river bottom morphology information to a cloud computing center to filter the multi-source river feature parameters based on the river bottom morphology information.

[0056] In the following, the specific configuration of the parameter determination and evaluation module 20 will be described in detail. The parameter determination and evaluation module 20 further includes: based on the Doppler profiler in the flow monitoring device, deploying a Doppler profiler array at equal intervals along the water flow direction, the first technical index corresponding to the Doppler profiler array including vertical layer number and layer thickness resolution; based on the rotor flowmeter in the flow monitoring device, setting a fixed measurement point at a key monitoring cross-section, the second technical index corresponding to the fixed measurement point including measurement point density and flow velocity measurement accuracy; and according to the river depth and flow velocity gradient in the multi-source river feature parameters, jointly configuring the first technical index and the second technical index.

[0057] In the following, the specific configuration of the parameter determination and evaluation module 20 will be described in detail. The parameter determination and evaluation module 20 further includes: spatially aligning the ADCP walk-through track and the sampling points of the flow monitoring device, synchronously adjusting the communication protocol of the flow monitoring device, and determining data transmission delay; obtaining time synchronization accuracy through the data transmission delay; and according to the river depth and floating object density in the multi-source river feature parameters, configuring a data resampling mechanism of the flow monitoring device based on the time synchronization accuracy.

[0058] Below, the specific configuration of the parameter judgment evaluation module 20 will be described in detail. The parameter judgment evaluation module 20 further comprises: deploying a multi-source sensor network in the target river basin, the multi-source sensor network being used to collect the multi-source river feature parameters; generating a river section flow velocity distribution map based on the multi-source river feature parameters, and spatially aligning the ADCP track and the sampling points of the flow monitoring equipment with the river section flow velocity distribution map and GIS data.

[0059] Below, the specific configuration of the flow monitoring report generation module 30 will be described in detail. The flow monitoring report generation module 30 further comprises: triggering a cross-validation mechanism when the floating object density fluctuation exceeds the preset fluctuation interval and the data proportion under the data resampling mechanism is greater than the proportion threshold; determining a confidence interval using the cross-validation mechanism, and updating the confidence rating using the confidence interval.

[0060] Below, the specific configuration of the flow monitoring report generation module 30 will be described in detail. The flow monitoring report generation module 30 further comprises: locating a floating object tracking coordinate in the multi-source sensor network, and the flow monitoring equipment and the sonar detection equipment working cooperatively at the floating object tracking coordinate; collecting floating object tracking data through the floating object tracking coordinate, analyzing the influence of floating object density fluctuation on river flow, and configuring a preset fluctuation interval.

[0061] Below, the specific configuration of the flow monitoring report generation module 30 will be described in detail. The flow monitoring report generation module 30 further comprises: issuing a floating object shielding avoidance reminder when the floating object density fluctuation exceeds the preset fluctuation interval, the floating object shielding avoidance reminder being bound to the floating object tracking coordinate and the floating object dense area marker.

[0062] Below, the specific configuration of the flow monitoring report generation module 30 will be described in detail. The flow monitoring report generation module 30 further comprises: deploying an edge computing node according to the floating object tracking coordinate, the edge computing node being in communication connection with a cloud computing center; the edge computing node receiving the floating object tracking coordinate bound to the floating object shielding avoidance reminder, predicting the river influence range under the floating object aggregation trend, and elastically expanding the floating object dense area.

[0063] The multi-source data fusion river flow intelligent monitoring system provided by the embodiments of the present application can execute the multi-source data fusion river flow intelligent monitoring method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0064] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server, the various units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific name of each functional unit is only for the convenience of mutual differentiation, and is not used to limit the protection scope of the present application.

[0065] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for intelligent monitoring of river flow through multi-source data fusion, characterized in that, The method comprises: In the target river basin, collect multi-source river characteristic parameters including river water depth, flow velocity gradient and floating object density, and configure parameter judgment criteria; Use a sonar detection device to obtain river bottom morphology information of the target river basin; Upload the river bottom morphology information to a cloud computing center, and filter the multi-source river characteristic parameters based on the river bottom morphology information; Connect a flow monitoring device to evaluate the feasibility of ADCP walk-through flow measurement based on the parameter judgment criteria, the flow monitoring device comprising a rotor flowmeter and a Doppler profiler; specifically further comprising: Based on the Doppler profiler in the flow monitoring device, deploy a Doppler profiler array at equal intervals along the water flow direction, and the first technical index corresponding to the Doppler profiler array includes vertical layer number and layer thickness resolution; Based on the rotor flowmeter in the flow monitoring device, set a fixed measurement point at a key monitoring section, and the second technical index corresponding to the fixed measurement point includes measurement point density and flow velocity measurement accuracy; Jointly configure the first technical index and the second technical index according to the river water depth and the flow velocity gradient in the multi-source river characteristic parameters; Spatially align the ADCP walk-through trajectory and the sampling points of the flow monitoring device, synchronously adjust the communication protocol of the flow monitoring device, and determine the data transmission time delay; Obtain time synchronization accuracy through the data transmission time delay; Configure the data resampling mechanism of the flow monitoring device based on the time synchronization accuracy according to the river water depth and the floating object density in the multi-source river characteristic parameters; When the ADCP effective measurement probability is lower than a preset threshold, synchronously adjust the sampling frequency and the channel coverage range of the flow monitoring device, perform coordinate correction on the ADCP walk-through section data and the discrete point data of the flow monitoring device under the parameter judgment criteria, and generate a flow monitoring report with a confidence rating.

2. The intelligent monitoring method of river flow using multi-source data fusion as claimed in claim 1, wherein, The method comprises: In the target river basin, deploy a multi-source sensor network for collecting the multi-source river characteristic parameters; Based on the multi-source river characteristic parameters, generate a river section flow velocity distribution map, and spatially align the ADCP walk-through trajectory and the sampling points of the flow monitoring device based on the river section flow velocity distribution map and GIS data.

3. The intelligent river flow monitoring method of multi-source data fusion as claimed in claim 2, wherein, Perform coordinate correction on the ADCP walk-through section data and the discrete point data of the flow monitoring device under the parameter judgment criteria, and generate a flow monitoring report with a confidence rating, specifically further comprising: When the floating object density fluctuation exceeds a preset fluctuation interval, and the data proportion under the data resampling mechanism is greater than a proportion threshold, trigger a cross-validation mechanism; Determine a confidence interval based on the cross-validation mechanism, and update the confidence rating using the confidence interval.

4. The intelligent river flow monitoring method of multi-source data fusion as claimed in claim 3, wherein, The method comprises: In the multi-source sensor network, locate a floating object tracking coordinate, and the flow monitoring device and the sonar detection device work cooperatively at the floating object tracking coordinate; Collect floating object tracking data through the floating object tracking coordinate, analyze the influence of floating object density fluctuation on river flow, and configure a preset fluctuation interval.

5. The intelligent river flow monitoring method of multi-source data fusion as claimed in claim 4, wherein, When the density of the floating object fluctuates beyond the preset fluctuation range, a floating object shelter avoidance reminder is sent, which is bound to the floating object tracking coordinates and the floating object dense area mark.

6. The intelligent river flow monitoring method of multi-source data fusion as claimed in claim 5, wherein, According to the floating object tracking coordinates, an edge computing node is deployed, which is in communication connection with a cloud computing center. The edge computing node receives the floating object tracking coordinates bound to the floating object shelter avoidance reminder, predicts the riverway influence range under the floating object aggregation trend, and elastically expands the floating object dense area.

7. The intelligent monitoring system of river flow by multi-source data fusion, characterized in that, The system is used to implement the multi-source data fusion riverway flow intelligent monitoring method according to any one of claims 1 to 6, and the system comprises: A riverway characteristic parameter acquisition module is configured to acquire multi-source riverway characteristic parameters including riverway water depth, flow velocity gradient and floating object density in a target riverway basin, and configure a parameter judgment benchmark. A parameter judgment evaluation module is configured to connect a flow monitoring device, evaluate the feasibility of ADCP underway flow measurement according to the parameter judgment benchmark, and the flow monitoring device comprises a rotor flow velocity meter and a Doppler profiler. A flow monitoring report generation module is configured to, when the ADCP effective measurement probability is lower than a preset threshold, synchronously adjust the sampling frequency and the channel coverage range of the flow monitoring device, perform coordinate correction on the ADCP underway section data and the discrete point data of the flow monitoring device under the parameter judgment benchmark, and generate a flow monitoring report with a confidence level.

Images