Radar target detection method, device, equipment and medium based on EMD
Through the EMD-based radar target detection method, three-dimensional timing modeling of bridge structures and damage feature extraction are solved, and the problems of insufficient sensors and noise interference in traditional detection methods are improved, and the accuracy and reliability of bridge structure damage detection are improved.
Patent Information
- Application Number
- CN202411246592.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The existing bridge structure damage detection methods are insufficient or unreasonable in the number of sensors or unreasonable arrangement, resulting in inaccurate detection results, and serious noise and drift problems in data analysis, which affects the accuracy of the detection results.
Using radar target detection method based on empirical modal decomposition (EMD), the radar system can obtain detection data of bridge structure, perform three-dimensional timing modeling, extract structural damage characteristics, and perform empirical modal decomposition to obtain the intrinsic characteristics of bridge structure. The modal function IMF component is used to evaluate structural damage.
The accuracy of bridge structure damage detection is improved, and the bridge structure status can be more effectively reflected, noise interference is reduced, and the reliability of detection results can be improved.
Smart Images

Figure CN118758975B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to an EMD-based radar target detection method, device, equipment and medium. Background Art
[0002] As a key component of transportation infrastructure, the safety and integrity of the bridge structure are crucial to the normal operation of transportation. With the increase in the service life of the bridge, the increase in traffic flow and the influence of environmental factors, various damages will inevitably occur in the bridge structure. Therefore, timely and accurate detection of the damage of the bridge structure has become an important task to ensure the safety of the bridge. At present, sensors are usually placed on the target bridge to detect the damage of the target bridge through the detection data of the sensor. However, the insufficient number of sensors or unreasonable arrangement may cause the damage information of key parts to be unable to be effectively collected, and the noise and drift problems in the data collection process will also bring difficulties to the subsequent data analysis and damage judgment, which will lead to the inaccurate results of the structural damage detection of the target bridge. Therefore, how to improve the accuracy of the structural damage detection results of the target bridge has become a problem that needs to be solved urgently. Summary of the invention
[0003] The present invention provides an EMD-based radar target detection method, device, equipment and medium to solve the technical problem of how to improve the accuracy of structural damage detection results for a target bridge.
[0004] In a first aspect, a radar target detection method based on EMD is provided, comprising:
[0005] Acquire a bridge structure detection data set detected by the radar system for the target bridge within a preset time period;
[0006] Perform three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure;
[0007] Extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data;
[0008] Perform EMD processing on the structural damage characteristic data to obtain the IMF component set of the bridge structure's intrinsic mode function;
[0009] Structural damage assessment is performed on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0010] In a second aspect, a radar target detection device based on EMD is provided, comprising:
[0011] An acquisition module is used to acquire a set of bridge structure detection data detected by the radar system for a target bridge within a preset time period;
[0012] The first processing module is used to perform three-dimensional time series modeling according to the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure;
[0013] The second processing module is used to extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data;
[0014] The third processing module is used to perform EMD processing on the structural damage characteristic data to obtain an IMF component set of the bridge structure intrinsic mode function;
[0015] The fourth processing module is used to perform structural damage assessment on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0016] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned EMD-based radar target detection method when executing the computer program.
[0017] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned EMD-based radar target detection method are implemented.
[0018] In the scheme implemented by the above-mentioned EMD-based radar target detection method, device, equipment and medium, by obtaining a set of bridge structure detection data detected by the radar system for the target bridge within a preset time period, and performing three-dimensional time series modeling based on the bridge structure detection data set, a three-dimensional time series model of the bridge structure is obtained, and the three-dimensional time series model of the bridge structure can be further extracted to obtain structural damage feature data, so that the structural damage feature data can be subjected to empirical mode decomposition (EMD) processing to obtain a set of bridge structure intrinsic mode function (IMF) components, and then each bridge structure IMF component in the bridge structure IMF component set can be subjected to structural damage assessment to obtain more accurate target structure damage data, which is beneficial to improving the accuracy of the structural damage detection results for the target bridge. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0020] Figure 1 Schematic diagram of an application environment of a radar target detection method based on EMD in one embodiment of the present invention;
[0021] Figure 2 It is a flow chart of a radar target detection method based on EMD in one embodiment of the present invention;
[0022] Figure 3 is a structural schematic diagram of a radar target detection device based on EMD in one embodiment of the present invention;
[0023] Figure 4 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;
[0024] Figure 5 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION
[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.
[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0027] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.
[0028] At present, in an existing bridge health monitoring method of adaptive signal decomposition and identification, the trend items and burrs in the response signal can be removed to eliminate abnormal factors in the response signal, and the response signal can be decomposed and reorganized to improve the accuracy of health status monitoring of the existing bridge simply supported beam structure, so as to achieve the purpose of accurately monitoring the health status of the bridge. In the existing method, although three preprocessing algorithms (exploratory data analysis method, Elada method and trinomial least squares method) are combined to realize the preprocessing of the collected response signal, it can ensure that the signal is not affected by noise to a certain extent. However, simply removing the influence of noise in the signal may still cause the health monitoring results of the bridge to be inaccurate because the signal itself is not accurate enough or cannot better and more comprehensively reflect the state of the bridge structure.
[0029] The radar target detection method based on EMD provided in the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the server through a network. For example, taking the scenario of structural damage assessment for a target bridge as an example, the server can obtain the bridge structure detection data set detected by the radar system for the target bridge within a preset period of time, or the target user can upload the bridge structure detection data set detected by the radar system for the target bridge within a preset period of time through the client. Among them, the target user can be a manager or R&D personnel who assesses the damage of the bridge structure, and this application does not limit this.
[0030] Accordingly, the server can obtain the bridge structure detection data set detected by the radar system for the target bridge within a preset period of time, and perform three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure, so as to further extract the structural damage characteristics of the three-dimensional time series model of the bridge structure, and obtain structural damage characteristic data that better and more comprehensively reflects the state of the bridge structure, so that the structural damage characteristic data can be processed by empirical mode decomposition (EMD) to obtain a bridge structure intrinsic mode function (IMF) component set, so as to perform structural damage assessment on each bridge structure IMF component in the bridge structure IMF component set, obtain the target structural damage data of the target bridge, and then push the target structural damage data to the target user, and feed back the target structural damage data to the client. Accordingly, the client can receive the target structural damage data from the server, and can display the target structural damage data on the client for the target user to query or browse. By adopting the radar target detection method based on EMD provided in this application, the accuracy of the structural damage detection results for the target bridge can be improved.
[0031] The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.
[0032] See also Figure 2 As shown, Figure 2 A schematic flow chart of a radar target detection method based on EMD provided in an embodiment of the present invention comprises the following steps:
[0033] S10: Acquire a bridge structure detection data set detected by the radar system for the target bridge within a preset time period.
[0034] The radar system can perform bridge structure detection for the target bridge in the embodiment of the present application, and the radar system can be an electronic device that uses radio waves to detect the target bridge and obtain relevant detection information. The target bridge can be a bridge that needs to be inspected for bridge structure, that is, a bridge that needs to use the method provided by the present application to determine whether there is structural damage.
[0035] The preset time period may be a preset time period for performing bridge structure inspection on the target bridge, and the preset time period may be preset by the target user or set by the system by default, and this application does not limit this. For example, if it is preset to perform bridge structure inspection on the target bridge within the next month, the preset time period may be the next month, and this application does not limit this.
[0036] The bridge structure detection data set may include one or more bridge structure detection data, and the bridge structure detection data may be detection data obtained after the radar system detects the target bridge within a preset period of time. The bridge structure detection data may include the bridge structure image to be mentioned below, and optionally, the bridge structure detection data may also include bridge physics related data (such as vibration data, etc.), which is not limited in this application.
[0037] S20: Perform three-dimensional time series modeling according to the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure.
[0038] The three-dimensional time series model of the bridge structure can be used to indicate the three-dimensional time series model corresponding to the bridge structure of the target bridge obtained after three-dimensional time series modeling based on the bridge structure detection data set. It is understandable that the three-dimensional time series model of the bridge structure can show the three-dimensional structural state corresponding to the target bridge at different time points, and reflect the change state of the bridge structure of the target bridge over time, and this application does not limit this.
[0039] It should be understood that performing three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure refers to the process of constructing a three-dimensional time series model of the bridge structure. Among them, step S20, that is, performing three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure, includes the following steps:
[0040] S21: Acquire, from the bridge structure detection data set, a first bridge structure image subset corresponding to the target bridge at a first time, and a second bridge structure image subset corresponding to the target bridge at a second time;
[0041] S22: performing three-dimensional modeling of the bridge structure according to each first bridge structure image in the first bridge structure image subset and radar basic data of the radar system to obtain a first bridge structure three-dimensional image;
[0042] S23: performing three-dimensional modeling of the bridge structure according to each second bridge structure image in the second bridge structure image subset and radar basic data of the radar system to obtain a second bridge structure three-dimensional image;
[0043] S24: Establishing a time-series structure of the first three-dimensional bridge structure image and the second three-dimensional bridge structure image to obtain a three-dimensional time-series model of the bridge structure.
[0044] The first bridge structure image subset may include one or more first bridge structure images, which may be used to indicate a bridge structure image obtained after the radar system performs bridge structure detection on the target bridge at the first time. The first time may be any time within a preset time period, and this application does not impose any limitation on this.
[0045] The second bridge structure image subset may include one or more second bridge structure images, which may be used to indicate a bridge structure image obtained after the radar system performs bridge structure detection on the target bridge at a second time. The second time may be any time other than the first time within a preset period, and this application does not limit this.
[0046] This application is explained by taking the example that the server obtains the first bridge structure image subset and the second bridge structure image subset from the bridge structure detection data set to construct a three-dimensional time series model of the bridge structure, which does not constitute a limitation on this application. Optionally, the server can obtain a bridge structure image subset corresponding to other times (such as the third time and the fourth time) from the bridge structure detection data set, and / or obtain other types of data (such as bridge physics-related data) from the bridge structure detection data set to further construct a three-dimensional time series model of the bridge structure based on these data, and this application does not limit this.
[0047] The radar basic data can be used to indicate relevant basic parameters of the radar system, such as the current position of the radar, the current angle of the radar, the propagation time of the radar signal, the transmission frequency of the radar, the antenna gain of the radar, the internal delay of the radar system and the air dielectric constant, etc., which are not limited in this application. The first bridge structure three-dimensional image can be used to indicate the three-dimensional image of the bridge structure obtained after the bridge structure three-dimensional modeling is performed according to the first bridge structure image and the radar basic data.
[0048] It should be understood that performing three-dimensional bridge structure modeling according to each first bridge structure image in the first bridge structure image subset and the radar basic data of the radar system to obtain the first bridge structure three-dimensional image refers to the process of constructing the first bridge structure three-dimensional image corresponding to the first time. Among them, step S22, that is, performing three-dimensional bridge structure modeling according to each first bridge structure image in the first bridge structure image subset and the radar basic data of the radar system to obtain the first bridge structure three-dimensional image, includes the following steps:
[0049] S221: preprocessing each first bridge structure image in the first bridge structure image subset to obtain a first bridge structure processed image set;
[0050] S222: performing perspective differentiation processing on each first bridge structure processed image in the first bridge structure processed image set to obtain a first multi-perspective bridge structure image set;
[0051] S223: determining a first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and radar basic data;
[0052] S224: performing region division processing on each first bridge structure point cloud coordinate in the first bridge structure point cloud set to obtain a first bridge structure divided point cloud coordinate set;
[0053] S225: Performing surface reconstruction processing on each first bridge structure division point cloud coordinate in the first bridge structure division point cloud coordinate set to obtain a first bridge structure three-dimensional image.
[0054] The first bridge structure processed image set may include one or more first bridge structure processed images, and the first bridge structure processed image may be used to indicate the bridge structure processed image obtained after preprocessing the first bridge structure image. Optionally, the server may obtain actual relevant data of the bridge, such as field survey data, etc., to further perform denoising on the first bridge structure image based on the actual relevant data of the bridge, so as to reduce the impact of environmental noise and interference on the data, and calibrate the zero point position and amplitude of the data, so as to improve the accuracy of the data.
[0055] The first multi-view bridge structure image set may include one or more first multi-view bridge structure images, and the first multi-view bridge structure image may be used to indicate a bridge structure image obtained after performing viewpoint differentiation processing on the first bridge structure processed image. In order to obtain detailed structural information of each angle of the bridge structure, the radar system may scan and inspect the bridge from multiple viewpoints, and at this time, the radar system may collect multiple groups of bridge structure images from different viewpoints.
[0056] The first bridge structure point cloud coordinate set may include one or more first bridge structure point cloud coordinates, and the first bridge structure point cloud coordinates may be used to indicate the point cloud coordinates obtained by determining the point cloud coordinates of each first multi-view bridge structure image and radar basic data.
[0057] It should be understood that determining the first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and the radar basic data refers to the process of determining the first bridge structure point cloud coordinate set corresponding to the first time. Among them, step S223, that is, determining the first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and the radar basic data, includes the following steps:
[0058] S2231: Acquire a first-perspective bridge structure image subset and a second-perspective bridge structure image subset from the first multi-perspective bridge structure image set;
[0059] S2232: Acquire a first-perspective marker point coordinate subset from the first-perspective bridge structure image subset, and acquire a second-perspective marker point coordinate subset from the second-perspective bridge structure image subset;
[0060] S2233: calculating a position vector of each first-view mark point coordinate in the first-view mark point coordinate subset to obtain a first-view position vector;
[0061] S2234: calculating a position vector of each second-view mark point coordinate in the second-view mark point coordinate subset to obtain a second-view position vector;
[0062] S2235: Calculating a position transformation parameter according to the first viewing angle position vector and the second viewing angle position vector to determine a first position offset parameter;
[0063] S2236: performing registration processing on each first-perspective bridge structure image in the first-perspective bridge structure image subset and each second-perspective bridge structure image in the second-perspective bridge structure image subset according to the first position offset parameter to obtain a first bridge structure registered image;
[0064] S2237: Determine a first bridge structure point cloud coordinate set according to the first bridge structure registration image and radar basic data.
[0065] The first-perspective bridge structure image subset may include one or more first-perspective bridge structure images, which may be used to indicate a bridge structure image obtained after the radar system scans and detects the bridge structure from a first perspective. The first perspective may be any perspective in the multi-perspective scanning and detection process of the radar system, and this application does not limit this.
[0066] The second-perspective bridge structure image subset may include one or more second-perspective bridge structure images, which may be used to indicate the bridge structure image obtained after the radar system scans and detects the bridge structure from the second perspective. The second perspective may be any perspective other than the first perspective during the multi-perspective scanning and detection process of the radar system, and the present application does not impose any limitation on this. In other words, the second perspective and the first perspective may be different perspectives.
[0067] The first perspective marker point coordinate subset may include one or more first perspective marker point coordinates, which may be used to indicate the coordinates of a specific marker point of the target bridge at the first perspective. The second perspective marker point coordinate subset may include one or more second perspective marker point coordinates, which may be used to indicate the coordinates of a specific marker point of the target bridge at the second perspective.
[0068] The specific marking point of the target bridge can be a specific point in the target bridge that is obvious and unique and easy to identify at any viewing angle. Optionally, when the server determines the point cloud coordinates based on any two viewing angles (such as the first viewing angle and the second viewing angle), the specific point that is easy to identify at both viewing angles can be selected to perform registration processing on the bridge structure images at different viewing angles, thereby determining a more accurate point cloud coordinate set, and this application does not impose any restrictions on this.
[0069] The first perspective position vector can be used to indicate the position vector obtained after the position vector is calculated according to the coordinates of each first perspective marker point. The second perspective position vector can be used to indicate the position vector obtained after the position vector is calculated according to the coordinates of each second perspective marker point. It can be understood that there can be at least two perspective marker points under each perspective to better determine the perspective position vector under each perspective. Optionally, when there are more than two perspective marker points under each perspective, the server can determine multiple perspective position vectors based on the more than two perspective marker points, and the present application does not limit this.
[0070] For example, taking the specific marker points of the target bridge as points A, B, and C, the first-view marker point coordinate subset can be , , , the coordinate subset of the second perspective marker points can be , , , then the first perspective position vector can be , , , the second viewing angle position vector can be , , .
[0071] The first position offset parameter can be used to indicate the position offset parameter determined after calculating the position transformation parameter based on the first perspective position vector and the second perspective position vector. Optionally, the server can calculate (such as the least squares method, etc.) based on the correspondence between the perspective marker point coordinates to solve the transformation parameter that can transform the bridge structure under the first perspective (such as the first perspective position vector) to the bridge structure under the second perspective (such as the second perspective position vector), that is, the above-mentioned position offset parameter. Optionally, the position offset parameter can be the corresponding offset transformation parameter transformed by rotation, translation and / or scaling, etc., and this application does not limit this.
[0072] The first bridge structure registration image can be used to indicate the bridge structure registration image obtained after each first-perspective bridge structure image and each second-perspective bridge structure image are registered according to the first position offset parameter. That is, after the server determines the first position offset parameter, the bridge structure images at different perspectives (i.e., the first-perspective bridge structure image and the second-perspective bridge structure image) can be accurately registered according to the first position offset parameter, thereby accurately aligning and matching the bridge structure images at different perspectives in spatial positions.
[0073] After the server obtains the accurately registered first bridge structure registered image, the server may further perform corresponding data processing and mathematical calculations based on the first bridge structure registered image and the radar basic data to determine the first bridge structure point cloud coordinate set.
[0074] For example, taking the radar basic data including the radar current position coordinates, radar scanning angle, radar signal propagation time and radar signal propagation speed in the air as an example, the server determines the point cloud coordinates of the target position point on the first bridge structure registration image according to the above radar basic data, as shown in the following formula:
[0075]
[0076] Among them, the point cloud coordinates of the target position point on the first bridge structure registration image can be , the horizontal coordinate of the target position point can be , the ordinate of the target position point can be , the vertical coordinate (or depth coordinate) of the target position point can be ; The radar's current position coordinates can be , the horizontal coordinate of the current position of the radar can be , the vertical coordinate of the current position of the radar can be , the vertical coordinate (or depth coordinate) of the current position of the radar can be ; The horizontal angle in the radar scanning angle can be , the vertical angle in the radar scanning angle is ; The propagation time of the radar signal is ; The propagation speed of radar signal in air is (usually approximated by the speed of light).
[0077] For steps S2231-S2237, the server obtains a first-perspective bridge structure image subset and a second-perspective bridge structure image subset from the first multi-perspective bridge structure image set, obtains a first-perspective marker point coordinate subset from the first-perspective bridge structure image subset, and obtains a second-perspective marker point coordinate subset from the second-perspective bridge structure image subset. The server can further calculate the position vector of each first-perspective marker point coordinate in the first-perspective marker point coordinate subset to obtain the first-perspective position vector, and calculate the position vector of each second-perspective marker point coordinate in the second-perspective marker point coordinate subset to obtain the second-perspective position vector, so that The position transformation parameters are calculated according to the first perspective position vector and the second perspective position vector to determine the first position offset parameter, and each first perspective bridge structure image in the first perspective bridge structure image subset and each second perspective bridge structure image in the second perspective bridge structure image subset are registered according to the first position offset parameter to obtain a first bridge structure registered image, and then a more accurate first bridge structure point cloud coordinate set can be determined according to the first bridge structure registered image and radar basic data, which is conducive to constructing a more accurate first bridge structure three-dimensional image based on the first bridge structure point cloud coordinate set in subsequent operation steps.
[0078] The first bridge structure division point cloud coordinate set may include one or more first bridge structure division point cloud coordinates, and the first bridge structure division point cloud coordinates may be used to indicate the bridge structure division point cloud coordinates obtained after each first bridge structure point cloud coordinate is subjected to regional division processing. The server can more accurately classify the regions corresponding to the various structures of the target bridge by performing regional division on the first bridge structure point cloud coordinates in the first bridge structure point cloud coordinate set, such as more accurately distinguishing the point cloud coordinate subset corresponding to the pier structure, the point cloud coordinate subset corresponding to the bridge deck structure, and the point cloud coordinate subset corresponding to the traction structure, thereby obtaining the first bridge structure division point cloud coordinate set that accurately divides and classifies the regions, and the present application does not impose any restrictions on this.
[0079] Furthermore, the server can perform surface reconstruction processing on each first bridge structure division point cloud coordinate after the area division, so as to convert the discrete first bridge structure division point cloud coordinate into a continuous and smooth surface model, thereby obtaining a first bridge structure three-dimensional image of the target bridge at the first time. Optionally, the server can use a triangulation method, a spline surface method or an implicit surface method to realize the process of surface reconstruction processing on the first bridge structure division point cloud coordinate, and this application does not limit this.
[0080] For steps S221-S225, the server pre-processes each first bridge structure image in the first bridge structure image subset to obtain a first bridge structure processed image set, and performs perspective differentiation processing on each first bridge structure processed image in the first bridge structure processed image set to obtain a first multi-perspective bridge structure image set. The first bridge structure point cloud coordinate set can be further determined based on each first multi-perspective bridge structure image in the first multi-perspective bridge structure image set and the radar basic data, so that each first bridge structure point cloud coordinate in the first bridge structure point cloud set can be region-divided to obtain a first bridge structure divided point cloud coordinate set, and then each first bridge structure divided point cloud coordinate in the first bridge structure divided point cloud coordinate set can be surface reconstructed to obtain an accurate first bridge structure three-dimensional image, which is beneficial for establishing a more accurate three-dimensional time series model of the bridge structure based on the first bridge structure three-dimensional image in subsequent steps.
[0081] The second bridge structure three-dimensional image can be used to indicate the bridge structure three-dimensional image obtained after the bridge structure three-dimensional modeling is performed based on the second bridge structure image and the radar basic data. It is understandable that the server can further perform the bridge structure three-dimensional modeling based on the second bridge structure image and the radar basic data corresponding to the second time, so as to obtain the second bridge structure three-dimensional image. Optionally, the server obtains the relevant content of the second bridge structure three-dimensional image, which can be referred to the server obtains the first bridge structure three-dimensional image, and this application will not repeat it here.
[0082] The server can store the three-dimensional images of the bridge structure corresponding to different times, such as the first three-dimensional image of the bridge structure corresponding to the first time, the second three-dimensional image of the bridge structure corresponding to the second time, and the three-dimensional images of the bridge structure corresponding to other times, in a data structure (such as an array, a linked list or a database) in chronological order, so as to use the three-dimensional image of the bridge structure corresponding to each time as an element in the data structure, thereby establishing a three-dimensional time series model of the bridge structure. Optionally, each element can be indexed by its corresponding time, and the three-dimensional image data and related attribute data (such as structural features, deformation data, etc.) at the corresponding time point can be used as the content to fill in the aforementioned time series data structure, thereby obtaining a three-dimensional time series model of the bridge structure, and this application does not impose any restrictions on this.
[0083] For steps S21-S24, the server obtains a first bridge structure image subset corresponding to the target bridge at the first time and a second bridge structure image subset corresponding to the target bridge at the second time from the bridge structure detection data set. It can perform three-dimensional modeling of the bridge structure according to each first bridge structure image in the first bridge structure image subset and the radar basic data of the radar system to obtain a first bridge structure three-dimensional image, and perform three-dimensional modeling of the bridge structure according to each second bridge structure image in the second bridge structure image subset and the radar basic data of the radar system to obtain a second bridge structure three-dimensional image, so that the first bridge structure three-dimensional image and the second bridge structure three-dimensional image can be time-series structured to obtain a three-dimensional time-series model of the bridge structure containing more feature information.
[0084] S30: extracting structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data.
[0085] Among them, the structural damage characteristic data can be used to indicate the characteristic data obtained after the structural damage characteristic extraction is performed on the three-dimensional time series model of the bridge structure. The structural damage characteristic data can be used to describe the damage status related information of the target bridge structure after being affected by various factors during daily use. It can be understood that by extracting the structural damage characteristics of the three-dimensional time series model of the bridge structure, structural damage characteristic data that better and more comprehensively reflects the state of the bridge structure can be obtained.
[0086] The structural damage characteristic data obtained in this application may include time-series structural damage characteristic data, and may also include non-time-series structural damage characteristic data, and this application does not impose any restrictions on this. In other words, the server can collect structural damage characteristic data that evolves over time based on the three-dimensional time-series model of the bridge structure, and can also collect non-time-series structural damage characteristic data at a specific moment or under specific conditions based on the three-dimensional time-series model of the bridge structure, such as peak data such as the local maximum deformation and maximum stress value of the structure under extreme weather conditions, and this application does not impose any restrictions on this.
[0087] Optionally, the server can perform deformation analysis on the three-dimensional time series model of the bridge structure to compare the geometric shape differences, displacements, strains and deformations of key points at different times of the bridge structure to obtain structural damage characteristics in the deformation analysis dimension. The server can perform vibration analysis on the three-dimensional time series model of the bridge structure to analyze the changes in modal parameters such as vibration frequency, vibration mode and damping ratio at different times to find abnormal vibration conditions that may indicate structural damage, thereby obtaining structural damage characteristics in the vibration analysis dimension.
[0088] Optionally, the server can determine the structural damage characteristics in different dimensions by performing material property evaluation, surface defect detection, stress distribution analysis, and topology optimization comparison on the three-dimensional time series model of the bridge structure, and the present application does not impose any restrictions on this. Optionally, the server can fuse the structural damage characteristics in different dimensions to highlight the abnormal areas, thereby obtaining more accurate structural damage characteristic data. Optionally, the server can fuse the temporal structural damage characteristics of multiple dimensions, and fuse the non-temporal structural damage characteristics of multiple dimensions, so that the temporal structural damage characteristic data and the non-temporal structural damage characteristic data can be decomposed and processed separately in the subsequent decomposition process, and the present application does not impose any restrictions on this.
[0089] Optionally, the server performs vibration analysis on the three-dimensional time series model of the bridge structure to obtain bridge vibration data, and performs deformation analysis on the three-dimensional time series model of the bridge structure to obtain stress-strain data, and then further fuses the bridge vibration data and stress-strain data based on energy fusion to obtain structural damage characteristic data. The process of the server obtaining the structural damage characteristic data can be described as follows:
[0090]
[0091] in, It can be used to represent structural damage characteristic data. Can be used to indicate time in a preset period; The weight of bridge vibration data can be expressed; It can be used to indicate the starting time of calculating the energy in the corresponding time interval. It can be used to indicate the end time of calculating the energy in the corresponding time interval; Can be used to indicate vibration amplitude; Can be used to indicate vibration frequency; Can be used to indicate the initial phase of vibration; Can be used to represent noise in vibration data; It can be used to represent the small time intervals after subdividing the time during the integral calculation process; It can be used to express the elastic coefficient of bridge structure materials; It can be used to represent the function of strain changing with time.
[0092] Optionally, the above example uses the fusion processing of bridge vibration data and stress-strain data as an example for illustration, which does not constitute a limitation on this application. The server can fuse structural damage feature data in multiple dimensions, and this application does not limit this. Optionally, the above example uses the fusion processing by energy fusion as an example, which does not constitute a limitation on this application. The server can use other fusion methods to achieve fusion processing, and this application does not limit this.
[0093] S40: Performing EMD processing on the structural damage characteristic data to obtain an IMF component set of the bridge structure intrinsic mode function.
[0094] By performing EMD on the structural damage characteristic data, the server can decompose the complex signal (i.e., structural damage characteristic data) into multiple IMFs and a residual term, which helps to deeply understand the inherent structure and characteristics of the structural damage characteristic data, thereby achieving more accurate assessment and prediction of the structural damage of the target bridge.
[0095] The bridge structure IMF component set may include one or more bridge structure IMF components, and the bridge structure IMF components may be used to indicate the IMF components obtained after the structural damage characteristic data is subjected to EMD processing. For example, in the case where the structural damage characteristic data includes vibration damage characteristic data, the server may decompose the vibration damage characteristic data into IMF components of different vibration frequencies to help discover possible structural damage or abnormal vibration modes, and this application does not impose any restrictions on this.
[0096] It should be understood that performing EMD processing on the structural damage characteristic data to obtain the IMF component set of the bridge structure intrinsic mode function refers to the process of performing EMD processing to obtain the IMF component set of the bridge structure. Among them, step S40, that is, performing EMD processing on the structural damage characteristic data to obtain the IMF component set of the bridge structure intrinsic mode function, includes the following steps:
[0097] S41: extracting IMF components from the structural damage characteristic data to obtain the first bridge structure IMF component;
[0098] S42: performing a subtraction operation on the structural damage characteristic data and the first bridge structure IMF component to obtain residual structural damage characteristic data;
[0099] S43: extracting IMF components from the residual structural damage characteristic data to obtain the IMF components of the second bridge structure;
[0100] S44: Determine a bridge structure IMF component set according to the first bridge structure IMF component and the second bridge structure IMF component.
[0101] The first bridge structure IMF component can be used to indicate the IMF component obtained after the IMF component extraction is performed on the structural damage characteristic data. It can be understood that the first bridge structure IMF component can be the IMF component obtained after the first EMD decomposition.
[0102] It should be understood that extracting the IMF components from the structural damage characteristic data to obtain the first bridge structure IMF components refers to the process of performing the first EMD decomposition. In step S41, extracting the IMF components from the structural damage characteristic data to obtain the first bridge structure IMF components includes the following steps:
[0103] S411: Identify local maximum and local minimum values of the structural damage characteristic data to obtain a first local structural damage maximum characteristic value and a first local structural damage minimum characteristic value;
[0104] S412: performing interpolation processing on the maximum eigenvalue of the first local structural damage to obtain an upper envelope of the first local structural damage;
[0105] S413: performing interpolation processing on the minimum eigenvalue of the first local structure damage to obtain a lower envelope of the first local structure damage;
[0106] S414: performing local mean calculation according to the first local structure damage upper envelope and the first local structure damage lower envelope to obtain first local structure damage mean data;
[0107] S415: Perform a subtraction operation on the structural damage characteristic data and the first local structural damage mean data to obtain a first bridge structure IMF component.
[0108] Among them, the first local structural damage maximum eigenvalue can be used to indicate the maximum eigenvalue obtained after the local maximum value of the structural damage characteristic data is identified. The first local structural damage minimum eigenvalue can be used to indicate the minimum eigenvalue obtained after the local minimum value of the structural damage characteristic data is identified. By identifying the local maximum value and the local minimum value of the structural damage characteristic data, the server can find out multiple local peaks and multiple local valleys in the structural damage characteristic data to reflect the changes and fluctuations of the structural damage characteristic data, which is helpful for constructing the envelope based on the multiple local peaks and multiple local valleys in the subsequent process.
[0109] The upper envelope of the first local structural damage can be used to indicate the upper envelope obtained after the interpolation processing of the maximum eigenvalue of the first local structural damage. The lower envelope of the first local structural damage can be used to indicate the lower envelope obtained after the interpolation processing of the minimum eigenvalue of the first local structural damage. The interpolation processing can be performed by a corresponding mathematical method (such as cubic spline interpolation) to fill data between multiple maximum points or multiple minimum values to form a curve that can wrap around the original data (i.e., the upper envelope) and a curve that can wrap around the original data (i.e., the lower envelope), and the present application does not impose any restrictions on this.
[0110] The first local structural damage mean data can be used to indicate the mean data obtained after the local mean calculation of the first local structural damage upper envelope and the first local structural damage lower envelope. In other words, the server can calculate the average of the corresponding values on the upper envelope and the lower envelope to remove the influence of the overall trend and average level in the original structural damage characteristic data, so that subsequent processing can focus more on the local fluctuations and changes of the data, thereby obtaining the first local structural damage mean data that helps to highlight the difference from the average trend in the original data.
[0111] In bridge structure health monitoring, by calculating the first local structural damage mean data, the first local structural damage mean data can be used as a benchmark for comparison and analysis with the subsequently extracted IMF components, so as to better understand the characteristics and development of structural damage, and more accurately discover large deviations from the first local structural damage mean data, thereby more clearly discovering abnormal damage in certain local areas of the bridge structure, which is not limited in this application.
[0112] For steps S411-S415, the server can obtain the maximum eigenvalue of the first local structural damage and the minimum eigenvalue of the first local structural damage by identifying the local maximum and local minimum of the structural damage characteristic data, and interpolate the maximum eigenvalue of the first local structural damage to obtain the first local structural damage upper envelope, and interpolate the minimum eigenvalue of the first local structural damage to obtain the first local structural damage lower envelope, and further perform local mean calculation based on the first local structural damage upper envelope and the first local structural damage lower envelope to obtain the first local structural damage mean data, thereby subtracting the structural damage characteristic data from the first local structural damage mean data to obtain the first bridge structure IMF component, which is conducive to gradually extracting IMF components of different frequencies and characteristics, and helps to highlight the local structural damage characteristics that are different from the average trend in the original data.
[0113] The residual structural damage characteristic data can be used to indicate the characteristic data obtained by subtracting the first bridge structure IMF component from the structural damage characteristic data after the first IMF component extraction is performed on the server. The second bridge structure IMF component can be used to indicate the IMF component obtained after the IMF component extraction is performed on the residual structural damage characteristic data. It can be understood that the second bridge structure IMF component can be the IMF component obtained after the second EMD decomposition.
[0114] It is understandable that after performing the second IMF component extraction, the server can also subtract the second bridge structure IMF component from the residual structure damage characteristic data to obtain another residual structure damage characteristic data, such as residual structure damage characteristic data 2, which is not limited in this application. Optionally, the server can perform a third EMD decomposition on the residual structure damage characteristic data 2, and then obtain an IMF component, such as a third bridge structure IMF component, which is not limited in this application. It is understandable that the server can repeat the EMD decomposition according to the above steps to obtain the decomposed bridge structure IMF components and a residual characteristic data, which is not limited in this application.
[0115] This application is explained by taking the example that the server determines the bridge structure IMF component set based on the first bridge structure IMF component and the second bridge structure IMF component, which does not constitute a limitation on this application. It is understandable that the bridge structure IMF component set may include all bridge structure IMF components obtained by EMD decomposition, and this application does not limit this.
[0116] The server performs the next EMD decomposition by subtracting the first bridge structure IMF component from the structural damage feature data, which helps to discover the features hidden in the original structural damage feature data that are not represented by the first bridge structure IMF component. It can further perform a deeper feature analysis on the complex original structural damage feature data. Through repeated EMD decomposition, it can more keenly capture subtle but critical damage information.
[0117] For example, the first EMD decomposition can help the server discover high-frequency vibration damage to the bridge structure within a specific time period, and the fifth EMD decomposition can help discover low-frequency, slowly developing damage trends caused by material aging. This application does not impose any restrictions on this.
[0118] For steps S41-S44, the server extracts the IMF components of the structural damage characteristic data to obtain the first bridge structure IMF component, and performs a subtraction operation on the structural damage characteristic data and the first bridge structure IMF component to obtain the residual structural damage characteristic data, so that the IMF components of the residual structural damage characteristic data can be extracted to obtain the second bridge structure IMF component, and then the bridge structure IMF component set can be determined based on the first bridge structure IMF component and the second bridge structure IMF component, which is conducive to gradually separating the components of different frequencies in the original structural damage characteristic data, so as to achieve a deeper and more refined analysis of the structural damage characteristic data.
[0119] S50: Performing structural damage assessment on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0120] The target structural damage data can be used to indicate the structural damage data determined after the structural damage assessment of each bridge structure IMF component. Optionally, the target structural damage data may include but is not limited to the structural damage location, structural damage type, structural damage degree and possible development trend of the structural damage of the target bridge, which is not limited in this application.
[0121] Optionally, the server can determine the structural damage characteristics of each bridge structure IMF component, such as by calculating the energy, entropy, kurtosis, skewness and other characteristic parameters of each bridge structure IMF component, and / or analyzing the spectral characteristics of each bridge structure IMF component (such as analyzing the main frequency components and frequency distribution range) to observe the morphology, periodicity and change trend of each bridge structure IMF component. This application does not impose any restrictions on this.
[0122] After determining the structural damage characteristics, the server can establish a structural damage assessment system based on the acquired structural damage characteristics, historical structural damage data, environmental related data, etc., such as setting energy or entropy thresholds to determine the existence and / or severity of structural damage, so as to accurately and comprehensively conduct structural damage assessment on each IMF component of the bridge structure, thereby obtaining more accurate target structural damage data that better meets the assessment criteria.
[0123] It can be seen that in the above scheme, the server obtains the bridge structure detection data set detected by the radar system for the target bridge within a preset time period, and performs three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure. The three-dimensional time series model of the bridge structure can be further extracted to obtain structural damage characteristics, and structural damage characteristic data can be obtained. Therefore, the structural damage characteristic data can be subjected to empirical mode decomposition (EMD) processing to obtain a set of bridge structure intrinsic mode function (IMF) components. Furthermore, each bridge structure IMF component in the bridge structure IMF component set can be subjected to structural damage assessment to obtain more accurate target structure damage data, which is beneficial to improving the accuracy of the structural damage detection results for the target bridge.
[0124] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0125] In one embodiment, a radar target detection device based on EMD is provided, and the radar target detection device based on EMD corresponds to the radar target detection method based on EMD in the above embodiment. Figure 3 As shown, the radar target detection device based on EMD includes an acquisition module 101, a first processing module 102, a second processing module 103, a third processing module 104 and a fourth processing module 105. The functional modules are described in detail as follows:
[0126] An acquisition module 101 is used to acquire a bridge structure detection data set detected by a radar system for a target bridge within a preset time period;
[0127] The first processing module 102 is used to perform three-dimensional time series modeling according to the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure;
[0128] The second processing module 103 is used to extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data;
[0129] The third processing module 104 is used to perform empirical mode decomposition (EMD) processing on the structural damage characteristic data to obtain an intrinsic mode function (IMF) component set of the bridge structure;
[0130] The fourth processing module 105 is used to perform structural damage assessment on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0131] In one embodiment, the first processing module 102 is used to perform three-dimensional time series modeling according to the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure, specifically for:
[0132] A first bridge structure image subset corresponding to the target bridge at the first time and a second bridge structure image subset corresponding to the target bridge at the second time are obtained from the bridge structure detection data set; three-dimensional modeling of the bridge structure is performed according to each first bridge structure image in the first bridge structure image subset and the radar basic data of the radar system to obtain a first bridge structure three-dimensional image; three-dimensional modeling of the bridge structure is performed according to each second bridge structure image in the second bridge structure image subset and the radar basic data of the radar system to obtain a second bridge structure three-dimensional image; a time series structure is established between the first bridge structure three-dimensional image and the second bridge structure three-dimensional image to obtain a three-dimensional time series model of the bridge structure.
[0133] In one embodiment, the first processing module 102 is used to perform three-dimensional modeling of the bridge structure according to each first bridge structure image in the first bridge structure image subset and radar basic data of the radar system to obtain the first bridge structure three-dimensional image, specifically for:
[0134] Preprocess each first bridge structure image in the first bridge structure image subset to obtain a first bridge structure processed image set; perform perspective differentiation processing on each first bridge structure processed image in the first bridge structure processed image set to obtain a first multi-perspective bridge structure image set; determine the first bridge structure point cloud coordinate set based on each first multi-perspective bridge structure image in the first multi-perspective bridge structure image set and radar basic data; perform region division processing on each first bridge structure point cloud coordinate in the first bridge structure point cloud set to obtain a first bridge structure division point cloud coordinate set; perform surface reconstruction processing on each first bridge structure division point cloud coordinate in the first bridge structure division point cloud coordinate set to obtain a first bridge structure three-dimensional image.
[0135] In one embodiment, the first processing module 102 is used to determine a first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and radar basic data, specifically for:
[0136] A first-perspective bridge structure image subset and a second-perspective bridge structure image subset are obtained from the first multi-perspective bridge structure image set; a first-perspective marker point coordinate subset is obtained from the first-perspective bridge structure image subset, and a second-perspective marker point coordinate subset is obtained from the second-perspective bridge structure image subset; a position vector is calculated for each first-perspective marker point coordinate in the first-perspective marker point coordinate subset to obtain a first-perspective position vector; a position vector is calculated for each second-perspective marker point coordinate in the second-perspective marker point coordinate subset to obtain a second-perspective position vector; a position transformation parameter is calculated based on the first-perspective position vector and the second-perspective position vector to determine a first position offset parameter; based on the first position offset parameter, each first-perspective bridge structure image in the first-perspective bridge structure image subset and each second-perspective bridge structure image in the second-perspective bridge structure image subset are registered to obtain a first bridge structure registered image; a first bridge structure point cloud coordinate set is determined based on the first bridge structure registered image and radar basic data.
[0137] In one embodiment, the third processing module 104 is used to perform empirical mode decomposition (EMD) processing on the structural damage characteristic data to obtain a set of intrinsic mode functions (IMF) components of the bridge structure, specifically for:
[0138] Perform IMF component extraction on the structural damage characteristic data to obtain the first bridge structure IMF component; perform subtraction operation on the structural damage characteristic data and the first bridge structure IMF component to obtain the residual structural damage characteristic data; perform IMF component extraction on the residual structural damage characteristic data to obtain the second bridge structure IMF component; determine the bridge structure IMF component set based on the first bridge structure IMF component and the second bridge structure IMF component.
[0139] In one embodiment, the third processing module 104 is used to extract IMF components from the structural damage characteristic data to obtain the IMF components of the first bridge structure, specifically for:
[0140] The local maximum and local minimum of the structural damage characteristic data are identified to obtain the maximum eigenvalue of the first local structural damage and the minimum eigenvalue of the first local structural damage; the maximum eigenvalue of the first local structural damage is interpolated to obtain the upper envelope of the first local structural damage; the minimum eigenvalue of the first local structural damage is interpolated to obtain the lower envelope of the first local structural damage; the local mean is calculated based on the upper envelope of the first local structural damage and the lower envelope of the first local structural damage to obtain the mean data of the first local structural damage; the structural damage characteristic data is subtracted from the first local structural damage mean data to obtain the IMF component of the first bridge structure.
[0141] The present invention provides a radar target detection device based on EMD, which obtains a bridge structure detection data set detected by a radar system for a target bridge within a preset time period, and performs three-dimensional time series modeling according to the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure. The three-dimensional time series model of the bridge structure can be further subjected to structural damage feature extraction to obtain structural damage feature data, so that the structural damage feature data can be subjected to empirical mode decomposition (EMD) processing to obtain a bridge structure intrinsic mode function (IMF) component set, and then each bridge structure IMF component in the bridge structure IMF component set can be subjected to structural damage assessment to obtain more accurate target structure damage data, which is beneficial to improving the accuracy of the structural damage detection result for the target bridge.
[0142] The specific definition of the radar target detection device based on EMD can be found in the above definition of the radar target detection method based on EMD, which will not be repeated here. Each module in the above-mentioned radar target detection device based on EMD can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0143] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, the functions or steps on the service side of a radar target detection method based on EMD are realized.
[0144] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, the functions or steps on the client side of a radar target detection method based on EMD are implemented.
[0145] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:
[0146] Acquire a bridge structure detection data set detected by the radar system for the target bridge within a preset time period;
[0147] Perform three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure;
[0148] Extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data;
[0149] Perform EMD processing on the structural damage characteristic data to obtain the IMF component set of the bridge structure's intrinsic mode function;
[0150] Structural damage assessment is performed on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0151] The present invention provides a computer device, which obtains a bridge structure detection data set detected by a radar system for a target bridge within a preset time period, and performs three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure. The three-dimensional time series model of the bridge structure can be further extracted for structural damage characteristics to obtain structural damage characteristic data, so that the structural damage characteristic data can be subjected to empirical mode decomposition (EMD) processing to obtain a bridge structure intrinsic mode function (IMF) component set, and then each bridge structure IMF component in the bridge structure IMF component set can be subjected to structural damage assessment to obtain more accurate target structure damage data, which is beneficial to improving the accuracy of the structural damage detection results for the target bridge.
[0152] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0153] Acquire a bridge structure detection data set detected by the radar system for the target bridge within a preset time period;
[0154] Perform three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure;
[0155] Extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data;
[0156] Perform EMD processing on the structural damage characteristic data to obtain the IMF component set of the bridge structure's intrinsic mode function;
[0157] Structural damage assessment is performed on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
[0158] The present invention provides a computer-readable storage medium, which obtains a bridge structure detection data set detected by a radar system for a target bridge within a preset time period, and performs three-dimensional time series modeling based on the bridge structure detection data set to obtain a three-dimensional time series model of the bridge structure. The three-dimensional time series model of the bridge structure can be further subjected to structural damage feature extraction to obtain structural damage feature data, so that the structural damage feature data can be subjected to empirical mode decomposition (EMD) processing to obtain a bridge structure intrinsic mode function (IMF) component set, and then each bridge structure IMF component in the bridge structure IMF component set can be subjected to structural damage assessment to obtain more accurate target structure damage data, which is beneficial to improving the accuracy of the structural damage detection results for the target bridge.
[0159] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.
[0160] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0161] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0162] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A radar target detection method based on EMD, characterized in that: The radar target detection method based on EMD comprises: Acquire a bridge structure detection data set detected by the radar system for the target bridge within a preset time period; Acquire, from the bridge structure detection data set, a first bridge structure image subset corresponding to the target bridge at a first time, and a second bridge structure image subset corresponding to the target bridge at a second time; Preprocessing each first bridge structure image in the first bridge structure image subset to obtain a first bridge structure processed image set; Performing perspective differentiation processing on each first bridge structure processed image in the first bridge structure processed image set to obtain a first multi-perspective bridge structure image set; Determine a first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and the radar basic data; Performing region division processing on each first bridge structure point cloud coordinate in the first bridge structure point cloud set to obtain a first bridge structure divided point cloud coordinate set; Performing surface reconstruction processing on each first bridge structure division point cloud coordinate in the first bridge structure division point cloud coordinate set to obtain a first bridge structure three-dimensional image; Performing three-dimensional modeling of the bridge structure according to each second bridge structure image in the second bridge structure image subset and radar basic data of the radar system to obtain a second bridge structure three-dimensional image; Establishing a time-series structure of the first three-dimensional bridge structure image and the second three-dimensional bridge structure image to obtain a three-dimensional time-series model of the bridge structure; Extracting structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data; Performing empirical mode decomposition (EMD) processing on the structural damage characteristic data to obtain an intrinsic mode function (IMF) component set of the bridge structure; A structural damage assessment is performed on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
2. The radar target detection method based on EMD according to claim 1, characterized in that: The step of determining a first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and the radar basic data comprises: Acquire a first-perspective bridge structure image subset and a second-perspective bridge structure image subset from the first multi-perspective bridge structure image set; Acquire a first-perspective marker point coordinate subset from the first-perspective bridge structure image subset, and acquire a second-perspective marker point coordinate subset from the second-perspective bridge structure image subset; Calculate the position vector of each first-view mark point coordinate in the first-view mark point coordinate subset to obtain a first-view position vector; Calculate the position vector of each second-view mark point coordinate in the second-view mark point coordinate subset to obtain a second-view position vector; Calculate a position transformation parameter according to the first viewing angle position vector and the second viewing angle position vector to determine a first position offset parameter; performing registration processing on each first-perspective bridge structure image in the first-perspective bridge structure image subset and each second-perspective bridge structure image in the second-perspective bridge structure image subset according to the first position offset parameter to obtain a first bridge structure registered image; A first bridge structure point cloud coordinate set is determined according to the first bridge structure registered image and the radar basic data.
3. The radar target detection method based on EMD according to claim 2, characterized in that: The structural damage characteristic data is subjected to empirical mode decomposition (EMD) processing to obtain a set of intrinsic mode functions (IMF) components of the bridge structure, including: Extracting IMF components from the structural damage characteristic data to obtain a first bridge structure IMF component; Subtracting the structural damage characteristic data from the first bridge structure IMF component to obtain residual structural damage characteristic data; Extracting IMF components from the residual structural damage characteristic data to obtain IMF components of a second bridge structure; A bridge structure IMF component set is determined according to the first bridge structure IMF component and the second bridge structure IMF component.
4. The radar target detection method based on EMD according to claim 3, characterized in that: The step of extracting IMF components from the structural damage characteristic data to obtain the first bridge structure IMF component includes: Identifying local maximum and local minimum values of the structural damage characteristic data to obtain a first local structural damage maximum characteristic value and a first local structural damage minimum characteristic value; Performing interpolation processing on the maximum eigenvalue of the first local structural damage to obtain an upper envelope of the first local structural damage; Performing interpolation processing on the first local structural damage minimum eigenvalue to obtain a first local structural damage lower envelope; Performing local mean calculation according to the first local structure damage upper envelope and the first local structure damage lower envelope to obtain first local structure damage mean data; The structural damage characteristic data is subtracted from the first local structural damage mean data to obtain a first bridge structure IMF component.
5. A radar target detection device based on EMD, characterized in that: The radar target detection device based on EMD comprises: An acquisition module is used to acquire a set of bridge structure detection data detected by the radar system for a target bridge within a preset time period; A first processing module is used to obtain, from the bridge structure detection data set, a first bridge structure image subset corresponding to the target bridge at a first time, and a second bridge structure image subset corresponding to the target bridge at a second time; The first processing module is further used to preprocess each first bridge structure image in the first bridge structure image subset to obtain a first bridge structure processed image set; The first processing module is further used to perform perspective differentiation processing on each first bridge structure processed image in the first bridge structure processed image set to obtain a first multi-perspective bridge structure image set; The first processing module is further used to determine a first bridge structure point cloud coordinate set according to each first multi-view bridge structure image in the first multi-view bridge structure image set and the radar basic data; The first processing module is further used to perform region division processing on each first bridge structure point cloud coordinate in the first bridge structure point cloud set to obtain a first bridge structure divided point cloud coordinate set; The first processing module is further used to perform surface reconstruction processing on each first bridge structure division point cloud coordinate in the first bridge structure division point cloud coordinate set to obtain a first bridge structure three-dimensional image; The first processing module is further used to perform three-dimensional modeling of the bridge structure according to each second bridge structure image in the second bridge structure image subset and the radar basic data of the radar system to obtain a second bridge structure three-dimensional image; The first processing module is further used to establish a time-series structure of the first three-dimensional bridge structure image and the second three-dimensional bridge structure image to obtain a three-dimensional time-series model of the bridge structure; The second processing module is used to extract structural damage features from the three-dimensional time series model of the bridge structure to obtain structural damage feature data; The third processing module is used to perform empirical mode decomposition (EMD) processing on the structural damage characteristic data to obtain an intrinsic mode function (IMF) component set of the bridge structure; The fourth processing module is used to perform structural damage assessment on each bridge structure IMF component in the bridge structure IMF component set to obtain target structural damage data of the target bridge.
6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the EMD-based radar target detection method according to any one of claims 1 to 4 is implemented.
7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the EMD-based radar target detection method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Nondestructive detection system for internal abnormality of woody body based on radar wave
CN106405061A
Bridge structure damage identification method and system
CN115937504A
Collection, calculation and inspection integrated bridge damage detection method and system
CN116626059A
Bridge structure health prediction method and system
CN116955948A
Bridge disease identification method and system
CN117889909A
