Scene-driven dam deformation monitoring method and system

Abstract

The invention discloses a scene-driven dam deformation monitoring method and system. The method comprises the following steps: S1, constructing a hydrological unit where a dam is located; s2, identifying a high-risk area according to historical disaster events of the hydrological unit; wherein the dam deformation monitoring network is arranged in a layered manner based on a high-risk area; and S3, dam deformation sensing is carried out according to the real-time scene monitoring data of the dam deformation monitoring network, and abnormal events in the monitoring scene are obtained. By adopting the technical scheme of the invention, the scientificity and pertinence of dam deformation monitoring distribution are effectively improved, a multi-level distributed monitoring network and intelligent perception are provided, and early warning and emergency response to abnormal events are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of safety monitoring, and in particular relates to a scenario-driven dam deformation monitoring method and system. Background Art

[0002] As core components of river flood control systems, dams not only store and allocate water resources but also play an irreplaceable role in flood prevention, disaster reduction, and socioeconomic development. my country has built over 100,000 dams of various types, making them a crucial pillar of the nation's water conservancy infrastructure. However, despite a high rate of safety compliance for large and medium-sized dams, some still present safety risks and have even experienced major accidents, due to factors such as natural disasters like floods, earthquakes, and landslides, as well as factors affecting design, construction, and operation and maintenance. Dam failure can cause significant casualties and property losses downstream, making dam safety monitoring and operation and maintenance management crucial.

[0003] Dam deformation monitoring is a key technical means of ensuring the structural safety and stable operation of dams. Traditional deformation monitoring relies primarily on equipment such as total stations and levels, along with regular manual inspections and traditional measurement methods. These methods suffer from limitations such as low monitoring frequency, insufficient automation, complex data processing, and delayed response times, making them unable to meet the demands of dynamic, intelligent monitoring of dam deformation in complex environments. With the application of new technologies such as sensors, the Internet of Things, and GNSS, dam deformation monitoring is gradually moving towards automation and intelligence, improving monitoring accuracy and efficiency. However, these methods still face numerous challenges in data fusion, anomaly identification, and risk warning.

[0004] Existing dam deformation monitoring systems often lack systematic analysis of extreme natural events and spatial risk distribution. The layout of monitoring points is disconnected from actual risk scenarios, resulting in inefficient resource utilization and difficulty in timely capturing abnormal changes in high-risk areas. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a scenario-driven dam deformation monitoring method and system, which effectively improves the scientificity and pertinence of dam deformation monitoring point layout, provides a multi-level distributed monitoring network and intelligent perception, and realizes early warning and emergency response to abnormal events.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A scenario-driven dam deformation monitoring method, comprising:

[0008] Step S1, constructing the hydrological unit where the dam is located;

[0009] Step S2: identifying high-risk areas based on historical disaster events in the hydrological unit; wherein a dam deformation monitoring network is layered based on the high-risk areas;

[0010] Step S3: dam deformation perception is performed based on the real-time scene monitoring data of the dam deformation monitoring network to obtain abnormal events in the monitoring scene.

[0011] Preferably, the historical disaster events in step S2 include: landslides and extreme rainfall events in the dam area in the hydrological unit.

[0012] Preferably, in step S2, a kernel density cluster analysis algorithm is used to extract high-risk areas based on the spatial locations of historical events.

[0013] Preferably, step S3 includes:

[0014] Step S31: Acquire real-time scene monitoring data of the dam deformation monitoring network, including rainfall, surface displacement, and deep displacement;

[0015] Step S32: Real-time detection of rainfall data is performed. When a rainstorm occurs, i.e., the 24-hour precipitation is 50 mm or more, step S33 is performed.

[0016] Step S33: Using the local outlier factor algorithm to perform time series anomaly detection distribution, real-time detection of surface displacement and deep displacement is performed, and an alarm is issued when an anomaly is detected;

[0017] Step S34: Output alarm information including the location, position and cause of the abnormality.

[0018] The present invention also provides a scenario-driven dam deformation monitoring system, comprising:

[0019] The first processing module is used to construct the hydrological unit where the dam is located;

[0020] The second processing module is used to identify high-risk areas based on historical disaster events in the hydrological unit; wherein, the dam deformation monitoring network is layered based on the high-risk areas;

[0021] The third processing module is used to perceive dam deformation based on the real-time scene monitoring data of the dam deformation monitoring network and obtain abnormal events in the monitoring scene.

[0022] As a preferred option, historical disaster events include: landslides and extreme rainfall events in the dam area of ​​the hydrological unit

[0023] Preferably, the second processing module uses a kernel density cluster analysis algorithm to extract high-risk areas based on the spatial locations of historical events.

[0024] Preferably, the third processing module senses dam deformation using an anomaly detection method based on real-time scene monitoring data from the dam deformation monitoring network to obtain abnormal events in the monitoring scene.

[0025] The present invention adopts dam deformation monitoring under the "hydrological unit-high-risk area-dam body monitoring" mode, which effectively improves the scientific nature of the spatial distribution of dam deformation monitoring and provides data support and decision-making basis for dam safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0027] Figure 1 This is a flow chart of a scenario-driven dam deformation monitoring method according to an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of dam deformation monitoring in the progressive manner of "watershed scenario - key areas - dam monitoring". DETAILED DESCRIPTION

[0029] 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.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Example 1:

[0032] like Figure 1 、 2 As shown, an embodiment of the present invention provides a scenario-driven dam deformation monitoring method, comprising:

[0033] Step S1, constructing the hydrological unit where the dam is located;

[0034] Step S2: identifying high-risk areas based on historical disaster events in the hydrological unit; wherein a dam deformation monitoring network is layered based on the high-risk areas;

[0035] Step S3: dam deformation perception is performed based on the real-time scene monitoring data of the dam deformation monitoring network to obtain abnormal events in the monitoring scene.

[0036] As an implementation of the embodiment of the present invention, step S1 includes:

[0037] Step S11: collecting basic geographic information of the dam area, including: digital elevation model (DEM), water body distribution, water system and its confluence relationship;

[0038] Step S12: Based on the topography, catchment area and watershed division principles, determine the boundaries and structural system of the hydrological unit where the dam is located, and form a hydrological unit spatial information database;

[0039] Step S13: Using watershed analysis tools, identify the upstream catchment area, inflow path, and downstream area that affect dam safety and establish corresponding hydrological-geographical spatial relationships.

[0040] As an implementation of the embodiment of the present invention, step S2 includes:

[0041] Step S21: Obtain historical disaster events of landslides and extreme rainfall in the past 10 years;

[0042] Step S22: Analyze the terrain DEM, water system and other spatial data, use the hydrological model to extract the watershed range, and use the Thiessen polygon method to refine it into spatial discrete units;

[0043] Step S23: extract high-risk areas based on spatial discrete units using a kernel density cluster analysis algorithm.

[0044] Furthermore, the first-level control points are arranged based on the dam, monitoring points are set up at important points in high-risk areas, and Beidou GNSS equipment is used to obtain surface displacement and deep displacement; monitoring points are arranged in the upstream and downstream basins of the dam at the first-level monitoring points to form a dam deformation monitoring network.

[0045] As an implementation of the embodiment of the present invention, step S3 includes:

[0046] Step S31: Acquire real-time scene monitoring data of the dam deformation monitoring network, including rainfall, surface displacement, and deep displacement;

[0047] Step S32: Real-time detection of rainfall data is performed. When a rainstorm occurs, i.e., the 24-hour precipitation is 50 mm or more, step S33 is performed.

[0048] Step S33: Using the local outlier factor algorithm to perform time series anomaly detection distribution, real-time detection of surface displacement and deep displacement is performed, and an alarm is issued when an anomaly is detected;

[0049] Step S34: Output alarm information including the location, position and cause of the abnormality.

[0050] Further, step S33 is specifically as follows:

[0051] Obtain surface displacement and deep displacement data from the monitoring network, remove noise, fill missing values, and perform normalization to ensure data quality;

[0052] According to data distribution and actual needs, select the appropriate number of neighboring points and time window length as the basic parameters of the local outlier factor algorithm;

[0053] In the time window, the neighboring points, local reachability density and local outlier factor of each data point are calculated to evaluate the density deviation of the data point;

[0054] The anomaly threshold is set to the top 10% of the highest historical value, and the local outlier factor of newly collected data points is monitored in real time. If the threshold is exceeded, an alarm is triggered to detect anomalies in a timely manner.

[0055] Example 2:

[0056] An embodiment of the present invention further provides a scenario-driven dam deformation monitoring system, comprising:

[0057] The first processing module is used to construct the hydrological unit where the dam is located;

[0058] The second processing module is used to identify high-risk areas based on historical disaster events in the hydrological unit; wherein, the dam deformation monitoring network is layered based on the high-risk areas;

[0059] The third processing module is used to perceive dam deformation based on the real-time scene monitoring data of the dam deformation monitoring network and obtain abnormal events in the monitoring scene.

[0060] As an implementation method of the present invention, historical disaster events include: landslides and extreme rainfall events in the dam area in the hydrological unit

[0061] As an implementation method of the embodiment of the present invention, the second processing module uses a kernel density cluster analysis algorithm to extract high-risk areas based on the spatial locations of historical events.

[0062] As an implementation method of an embodiment of the present invention, the third processing module perceives dam deformation using an anomaly detection method based on real-time scene monitoring data of the dam deformation monitoring network to obtain abnormal events in the monitoring scene.

[0063] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A scenario-driven dam deformation monitoring method, characterized in that: include: Step S1, constructing the hydrological unit where the dam is located; Step S2: identifying high-risk areas based on historical disaster events in the hydrological unit; wherein a dam deformation monitoring network is layered based on the high-risk areas; Step S3: dam deformation perception is performed based on the real-time scene monitoring data of the dam deformation monitoring network to obtain abnormal events in the monitoring scene.

2. The scenario-driven dam deformation monitoring method according to claim 1, characterized in that: The historical disaster events in step S2 include landslides and extreme rainfall events in the dam area of ​​the hydrological unit.

3. The scenario-driven dam deformation monitoring method according to claim 2, characterized in that: In step S2, a kernel density cluster analysis algorithm is used to extract high-risk areas based on the spatial locations of historical events.

4. The scenario-driven dam deformation monitoring method according to claim 3, characterized in that: Step S3 includes: Step S31: Acquire real-time scene monitoring data of the dam deformation monitoring network, including rainfall, surface displacement, and deep displacement; Step S32: Real-time detection of rainfall data is performed. When a rainstorm occurs, i.e., the 24-hour precipitation is 50 mm or more, step S33 is performed. Step S33: Using the local outlier factor algorithm to perform time series anomaly detection distribution, real-time detection of surface displacement and deep displacement is performed, and an alarm is issued when an anomaly is detected; Step S34: Output alarm information including the location, position and cause of the abnormality.

5. A scenario-driven dam deformation monitoring system, characterized in that: include: The first processing module is used to construct the hydrological unit where the dam is located; The second processing module is used to identify high-risk areas based on historical disaster events in the hydrological unit; wherein, the dam deformation monitoring network is layered based on the high-risk areas; The third processing module is used to perceive dam deformation based on the real-time scene monitoring data of the dam deformation monitoring network and obtain abnormal events in the monitoring scene.

6. The scenario-driven dam deformation monitoring system according to claim 4, characterized in that: Historical disaster events include landslides and extreme rainfall events in the dam area of ​​the hydrological unit.

7. The scenario-driven dam deformation monitoring system according to claim 5, characterized in that: The second processing module uses the kernel density cluster analysis algorithm to extract high-risk areas based on the spatial location of historical events.

8. The scenario-driven dam deformation monitoring system according to claim 5, characterized in that: The third processing module perceives dam deformation based on the real-time scene monitoring data of the dam deformation monitoring network through anomaly detection methods to obtain abnormal events in the monitoring scene.

Images