Analysis method, device and equipment for toppling deformable body and storage medium
Through small baseline integrated interference synthetic aperture radar and machine learning technology, the boundaries and pleated edges of the poured deformation are identified and their future deformation characteristics are predicted, which solves the problems of inaccurate monitoring and lack of prediction in the existing technology, and realizes prospective prevention and control of the poured deformation and ensures its stability.
Patent Information
- Application Number
- CN202510341077.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-21
- Publication Date
- 2025-07-29
AI Technical Summary
In the prior art, the monitoring means for dumping deformations have large equipment installation workload, poor accuracy, and lack of prediction functions, which cannot be promptly warned, resulting in threats to engineering safety and ecological balance.
A small baseline integrated interference synthetic aperture radar is used to obtain visual images, and the overall boundary and pleated edges of the poured deformation are identified through an edge extraction algorithm. Combined with digital elevation model and machine learning, it predicts its future moving trajectory and deformation characteristics, and realizes a prospective analysis of the poured deformation.
Accurate monitoring and prediction of poured deformation bodies is achieved, and prevention and control measures can be taken before the deformation body is actually destroyed to ensure its long-term stability and avoid disasters.
Smart Images
Figure CN120388047A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of geological disaster prevention and control, and particularly relates to an analysis method, device, equipment and storage medium for toppling deformation bodies. Background Art
[0002] A toppling deformation body is a progressive geological deformation body in which rock or soil masses bend, tilt or even break towards a free face under the action of gravity, geological structure or external disturbances (such as excavation, rainfall), and is commonly found in high-steep terrains such as the dam shoulders of hydropower stations and mine slopes. Its formation is affected by layered rock mass structures, groundwater softening and human activities, and is characterized by cracks at the slope top, extrusion at the slope foot, etc. Different from the shear sliding of landslides, it is mainly "bending - breaking".
[0003] The hazards of toppling deformation bodies are mainly manifested as engineering instability and ecological chain disasters caused by progressive failure: the bending - breaking process can cause irreversible deformation or even collapse of key structures such as the dam shoulders of hydropower stations, mine slopes, and traffic tunnels, directly threatening engineering safety and personnel lives; the expansion of tensile cracks at the rear edge of the toppling area may induce landslides or debris flows, and the risk doubles when extreme rainfall or earthquakes are superimposed. In addition, the stripping of the surface soil of the deformation body aggravates soil erosion and destroys the regional ecological balance.
[0004] In summary, it is necessary to monitor, analyze and control toppling deformation bodies to prevent the development of toppling deformation bodies from affecting infrastructure or causing disasters.
[0005] At present, there is little research on the monitoring and early warning technology for toppling deformation bodies. The commonly used monitoring methods still rely on measuring instruments such as theodolites, levels, and total stations to regularly measure the monitoring piers poured on the toppling deformation bodies, and then analyze the deformation development of the toppling deformation bodies. The problems of this method are: large amount of field work, inconvenient monitoring in adverse weather and at night, low accuracy, inability to accurately obtain the deformation depth and the change of the bending inclination angle of the toppling deformation body, and inability to provide continuous monitoring and timely early warning. In addition, there is also a technology that combines strain - gauge sensors with some detection sensors such as azimuth and angle to achieve the monitoring of toppling deformation bodies. Due to the large number of types of electronic products required, the workload and difficulty of installation and regular maintenance increase. Summary of the Invention
[0006] The main purpose of the present application is to provide an analysis method, device, equipment and storage medium for toppling deformation bodies to solve the problems in the prior art that the monitoring means for toppling deformation bodies have a large amount of equipment installation work, poor accuracy, and no prediction function.
[0007] To achieve the above object, the present application provides the following technical solutions:
[0008] A method for analyzing toppling deformable bodies, where the toppling deformable bodies are located within a preset area, and visual images of the preset area are obtained by small baseline integrated interferometric synthetic aperture radar based on a number of preset time periods. The analysis method includes:
[0009] Step S1, respectively extract the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body in each visual image through an edge extraction algorithm;
[0010] Step S2, respectively obtain the enclosed area of each overall boundary and the covered area of each folded edge;
[0011] Step S3, sequentially difference adjacent enclosed areas and adjacent covered areas according to the time process of all preset time periods, and obtain an enclosed area difference image and a covered area difference image based on the first difference;
[0012] Step S4, respectively extract the enclosed difference boundary of each enclosed area difference image and the covered difference boundary of each covered area difference image through the edge extraction algorithm;
[0013] Step S5, respectively obtain the elevation coordinate set of each enclosed difference boundary and the elevation coordinate set of each covered difference boundary based on the digital elevation model of the preset area;
[0014] Step S6, respectively train the elevation coordinate sets of all enclosed difference boundaries and the elevation coordinate sets of all covered difference boundaries through a machine learning machine, and obtain a number of enclosed difference boundary prediction coordinate sets and a number of covered difference boundary prediction coordinate sets based on a number of preset prediction steps;
[0015] Step S7, respectively obtain the coordinate enclosed area of each enclosed difference boundary prediction coordinate set and the coordinate enclosed area of each covered difference boundary prediction coordinate set, and respectively define them as a future movement trajectory of the toppling deformable body and a future movement trajectory of the folded toppling deformable body;
[0016] Step S8, judge whether all future movement trajectories of the toppling deformable bodies finally reach a coincidence state and whether all future movement trajectories of the folded toppling deformable bodies finally reach a coincidence state along the time process of all preset prediction steps;
[0017] Step S9, if both finally reach a coincidence state, then determine that the toppling deformable body reaches a stable state within all preset prediction steps.
[0018] As a further improvement of the present application, in step S8, after judging whether all future movement trajectories of the toppling deformable bodies finally reach a coincidence state and whether all future movement trajectories of the folded toppling deformable bodies finally reach a coincidence state along the time process of all preset prediction steps, it further includes:
[0019] Step S10, if at least one of the future movement trajectories of all toppling deformations or the future movement trajectories of all toppling deformation folds does not ultimately reach a coincident state, then execute Step S20;
[0020] Step S20, determine that the toppling deformation does not reach a stable state within all preset prediction steps, and mark the toppling deformation as a potentially deformed body for future disasters;
[0021] Step S30, respectively obtain the coordinate enclosing areas of each enclosed differential boundary prediction coordinate set;
[0022] Step S40, using the time process of all preset prediction steps as the horizontal axis of a rectangular coordinate system and the coordinate enclosing area as the vertical axis, generate a rectangular coordinate system;
[0023] Step S50, input the coordinate enclosing areas of each enclosed differential boundary prediction coordinate set into the rectangular coordinate system to obtain a number of enclosed differential boundary coordinate points;
[0024] Step S60, linearly fit all enclosed differential boundary coordinate points to obtain a toppling deformation increment function;
[0025] Step S70, determine whether the toppling deformation increment function converges. If it converges, then execute Step S80. If it does not converge, then execute Step S90;
[0026] Step S80, determine that the potentially deformed body for future disasters is in a convergent stable state;
[0027] Step S90, determine that the potentially deformed body for future disasters is in an accelerated deformation state.
[0028] As a further improvement of this application, in Step S40, using the time process of all preset prediction steps as the horizontal axis of a rectangular coordinate system and the coordinate enclosing area as the vertical axis, after generating a rectangular coordinate system, it further includes:
[0029] Step S100, input the coordinate enclosing areas of each covered differential boundary prediction coordinate set into the rectangular coordinate system to obtain a number of covered differential boundary coordinate points;
[0030] Step S200, linearly fit all covered differential boundary coordinate points to obtain a fold increment function;
[0031] Step S300, determine whether the fold increment function converges. If it converges, then execute Step S400. If it does not converge, then execute Step S500;
[0032] Step S400, determine that the toppling deformation is in an accelerated flow state;
[0033] Step S500, determine that the toppling deformable body is in a decelerating and stable state.
[0034] As a further improvement of this application, in step S1, the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body are respectively extracted from each visual image through an edge extraction algorithm, including:
[0035] Step S11, convert each visual image into a grayscale image respectively through the cv2.cvtColor() function of the OpenCV software package;
[0036] Step S12, obtain all color block edges of the current grayscale image through the Canny edge detection operator;
[0037] Step S13, define a corrosion structuring element with a preset pixel size;
[0038] Step S14, traverse all color block edges with the center of the corrosion structuring element;
[0039] Step S15, delete all paths traversed by the corrosion structuring element to obtain the corrosion image of the current grayscale image;
[0040] Step S16, perform difference between the current grayscale image and the current corrosion image to obtain the overall boundary and the folded edge.
[0041] As a further improvement of this application, in step S4, the enclosed differential boundary of each enclosed area differential image and the covered differential boundary of each covered area differential image are respectively extracted through the edge extraction algorithm, including:
[0042] Step S41, repeat steps S12 to S16 with the current enclosed area differential image as the execution subject to obtain the enclosed differential boundary of the current enclosed area differential image;
[0043] Step S42, repeat steps S12 to S16 with the current covered area differential image as the execution subject to obtain the covered differential boundary of the current covered area differential image.
[0044] As a further improvement of this application, in step S9, if the coincidence state is finally reached, it is determined that the toppling deformable body reaches a stable state within all preset prediction steps, and then, including:
[0045] Step S1000, obtain all visual images of the toppling deformable body and send them to an external visual monitoring terminal;
[0046] Step S2000, obtain the enclosed area of all overall boundaries and the covered area of all folded edges, and send them to an external visual monitoring terminal;
[0047] Step S3000: Obtain the coordinate enclosure areas of all enclosed differential boundary prediction coordinate sets and the coordinate enclosure areas of all covered differential boundary prediction coordinate sets, and send them to an external visual monitoring terminal.
[0048] To achieve the above object, the present application also provides the following technical solutions:
[0049] An analysis device for a toppling deformable body, the analysis device being applied to the analysis method as described above, the analysis device comprising:
[0050] An overall boundary and fold edge extraction module, configured to respectively extract the overall boundary of the toppling deformable body and the fold edge of the toppling deformable body in each visual image through an edge extraction algorithm;
[0051] An enclosed area and covered area acquisition module, configured to respectively acquire the enclosed area of each overall boundary and the covered area of each fold edge;
[0052] An enclosed area and covered area difference module, configured to sequentially difference adjacent enclosed areas and adjacent covered areas according to the time process of all preset time periods, and obtain an enclosed area difference image and a covered area difference image based on one-time difference;
[0053] A difference boundary extraction module, configured to respectively extract the enclosed difference boundary of each enclosed area difference image and the covered difference boundary of each covered area difference image through the edge extraction algorithm;
[0054] A boundary elevation coordinate set acquisition module, configured to respectively acquire the elevation coordinate set of each enclosed difference boundary and the elevation coordinate set of each covered difference boundary based on the digital elevation model of the preset area;
[0055] A difference boundary prediction module, configured to respectively train the elevation coordinate sets of all enclosed difference boundaries and the elevation coordinate sets of all covered difference boundaries through a machine learning machine, and obtain a plurality of enclosed difference boundary prediction coordinate sets and a plurality of covered difference boundary prediction coordinate sets based on a plurality of preset prediction steps;
[0056] A future movement trajectory acquisition module, configured to respectively acquire the coordinate enclosure area of each enclosed difference boundary prediction coordinate set and the coordinate enclosure area of each covered difference boundary prediction coordinate set, and respectively define them as a future movement trajectory of a toppling deformable body and a future movement trajectory of a fold of a toppling deformable body;
[0057] A future movement trajectory judgment module, configured to judge whether all future movement trajectories of the toppling deformable bodies finally reach a coincidence state and whether all future movement trajectories of the folds of the toppling deformable bodies finally reach a coincidence state along the time process of all preset prediction steps;
[0058] A steady state determination module, configured to determine that the toppling deformable body reaches a steady state within all preset prediction steps if a coincident state is finally reached for all of them.
[0059] To achieve the above object, the present application also provides the following technical solutions:
[0060] An electronic device includes a processor and a memory coupled to the processor. The memory stores program instructions executable by the processor. When the processor executes the program instructions stored in the memory, the above analysis method is implemented.
[0061] To achieve the above object, the present application also provides the following technical solutions:
[0062] A storage medium stores program instructions, which can implement the above analysis method when executed by a processor.
[0063] In this application, the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body are respectively extracted from each visual image through an edge extraction algorithm; the enclosed area of each overall boundary and the covered area of each folded edge are respectively obtained; the adjacent enclosed areas and the adjacent covered areas are successively differentiated according to the time process of all preset time periods, and a differential image of the enclosed area and a differential image of the covered area are obtained based on the first-order difference; the enclosed differential boundary of each differential image of the enclosed area and the covered differential boundary of each differential image of the covered area are respectively extracted through the edge extraction algorithm; the elevation coordinate sets of each enclosed differential boundary and the elevation coordinate sets of each covered differential boundary are respectively obtained based on the digital elevation model of the preset area; the elevation coordinate sets of all enclosed differential boundaries and the elevation coordinate sets of all covered differential boundaries are respectively trained through a machine learning machine, and a plurality of enclosed differential boundary prediction coordinate sets and a plurality of covered differential boundary prediction coordinate sets are respectively obtained based on a plurality of preset prediction steps; the coordinate enclosed areas of each enclosed differential boundary prediction coordinate set and the coordinate enclosed areas of the covered differential boundary prediction coordinate set are respectively obtained, and are respectively defined as a future movement trajectory of the toppling deformable body and a future movement trajectory of the folded toppling deformable body; it is judged whether all the future movement trajectories of the toppling deformable bodies finally reach a coincident state and whether all the future movement trajectories of the folded toppling deformable bodies finally reach a coincident state along the time process of all the preset prediction steps; if both finally reach a coincident state, it is determined that the toppling deformable body reaches a stable state within all the preset prediction steps. This application uses vision technology to analyze two deformation characteristics of the toppling deformable body, one is the global deformation characteristic, and the other is the local deformation characteristic. At the same time, the two analyzed deformation characteristics are respectively predicted, realizing the prospect and prediction of the potential deformation characteristics of the toppling deformable body. Finally, the disaster trend of the toppling deformable body is confirmed through the predicted future deformation characteristics, making the prevention and control of the toppling deformable body forward-looking. Certain prevention and control measures can be adopted before the slope actually undergoes deformation and failure, ensuring the long-term stability of the toppling deformable body. Description of the Drawings
[0064] Figure 1 It is a schematic flowchart of the steps of an embodiment of the analysis method of the toppling deformable body of this application;
[0065] Figure 2 It is a schematic diagram of the functional modules of an embodiment of the analysis device of the toppling deformable body of this application;
[0066] Figure 3 It is a schematic structural diagram of an embodiment of the electronic device of this application;
[0067] Figure 4 It is a schematic structural diagram of an embodiment of the storage medium of this application. Detailed Embodiments
[0068] Next, this application will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.
[0069] The terms "first", "second", and "third" in this application are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. 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 further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.
[0070] Referring to "embodiments" herein means that specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of this application. The phrase appearing in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.
[0071] As Figure 1 shown, this embodiment provides an embodiment of the analysis method of the toppling deformable body. In this embodiment, the toppling deformable body is located in a preset area, and the visual image of the preset area is obtained by small baseline integrated interferometric synthetic aperture radar based on a plurality of preset time periods.
[0072] Preferably, the toppling deformation body is a progressive geological deformation body in which rock mass or soil mass bends, tilts or even breaks towards the free face under the action of gravity, geological structure or external disturbances (such as excavation, rainfall), and is commonly found in high-steep terrains such as the dam shoulders of hydropower stations and mine slopes. Its formation is affected by layered rock mass structure, groundwater softening and human activities, and is characterized by cracks at the slope top, extrusion at the slope foot, etc. Different from the shear sliding of landslides, it is mainly "bending - breaking". The toppling deformation body is a slowly changing geological feature, and poor toppling deformation bodies are often accompanied by geological disasters such as landslide debris flows.
[0073] Preferably, the small baseline integrated InSAR is a detection device based on the differential interferometric measurement of short baseline set time series deformation failure analysis technology. This device usually directly monitors through satellites and does not require manual on-site placement of monitoring equipment.
[0074] Specifically, the analysis method includes the following steps:
[0075] Step S1, respectively extract the overall boundary of the toppling deformation body and the folded edge of the toppling deformation body in each visual image through an edge extraction algorithm.
[0076] Preferably, the fold is a bend formed by planar structures (such as bedding, cleavage or schistosity, etc.). Under the action of tectonic forces, or rather under the action of in-situ stress, the original occurrence of the rock strata is changed, not only causing the rock strata to tilt, but also forming various bends. A single bend is also called a fold. If the fold surface bends upward and the two sides tilt away from each other, it is called an anticline; if the fold surface bends downward and the two sides tilt towards each other, it is called a syncline. If the chronological order of the rock strata forming the fold is clear, then the fold with the older rock strata located at the core is called an anticline, and the fold with the younger rock strata located at the core is called a syncline. Under normal circumstances, the anticline is in the shape of an anticline and the syncline is in the shape of a syncline, which are two basic forms of folds. The larger individual fold can extend for dozens of kilometers. The folds cause obvious and continuous protrusions and depressions on the surface of the toppling deformation body, which can be detected by the edge extraction algorithm.
[0077] Step S2, respectively obtain the enclosed area of each overall boundary and the covered area of each folded edge.
[0078] Preferably, the overall boundary is the outermost boundary of the toppling deformation body, and the covered area is the folded area inside the toppling deformation body. In practical applications, if the fold is recognized as a line, if it is a non-branching line, the continuous individual line segments can be thickened to form the covered area, and the thickening degree should not affect the adjacent thickening process. For example, if the distance between two folds is 20m, then each can be thickened by at most 10m. If it is a branching line, the ends of each branch of the current line can be connected in sequence, and the formed closed area is the covered area.
[0079] Preferably, since the folds may move more frequently than the whole, if there are no branched lines, it is only necessary to thicken them by 5m.
[0080] Step S3, successively differentiate adjacent enclosed areas and adjacent covered areas according to the time processes of all preset time periods, and obtain an enclosed area differential image and a covered area differential image based on the first differentiation.
[0081] Preferably, since the deformation process of the toppling deformable body is relatively slow, the preset time period in this embodiment and the preset prediction steps in the following text can both be set to 15 natural days or 30 natural days.
[0082] Step S4, respectively extract the enclosed differential boundary of each enclosed area differential image and the covered differential boundary of each covered area differential image through an edge extraction algorithm.
[0083] Step S5, respectively obtain the elevation coordinate set of each enclosed differential boundary and the elevation coordinate set of each covered differential boundary based on the digital elevation model of the preset area.
[0084] Preferably, the acquisition density of the elevation coordinates can be set based on the resolution of the visual image. For example, one elevation point is collected per meter, or one elevation point is collected per ten centimeters if high-precision requirements are needed.
[0085] Step S6, respectively train the elevation coordinate sets of all enclosed differential boundaries and the elevation coordinate sets of all covered differential boundaries through a machine learning machine, and obtain several enclosed differential boundary prediction coordinate sets and several covered differential boundary prediction coordinate sets based on several preset prediction steps.
[0086] Step S7, respectively obtain the coordinate enclosed area of each enclosed differential boundary prediction coordinate set and the coordinate enclosed area of each covered differential boundary prediction coordinate set, and respectively define them as a future movement trajectory of the toppling deformable body and a future movement trajectory of the folds of the toppling deformable body.
[0087] Preferably, if the coordinate enclosed area is a closed area, it is directly obtained. If it is a non-closed area, the two ends of the line are connected to form a closed area.
[0088] Step S8, judge whether all the future movement trajectories of the toppling deformable bodies finally reach a coincidence state and whether all the future movement trajectories of the folds of the toppling deformable bodies finally reach a coincidence state along the time processes of all preset prediction steps.
[0089] Preferably, the coincidence state indicates that the toppling deformable body will stop deforming and form a stable body in the future. If there is no coincidence, it indicates that it will continue to deform and develop.
[0090] Step S9. If all reach the coincidence state finally, it is determined that the toppling deformable body reaches the stable state within all preset prediction steps.
[0091] Further, in step S8, it is judged whether the future movement trajectories of all toppling deformable bodies finally reach the coincidence state and whether the future movement trajectories of the folds of all toppling deformable bodies finally reach the coincidence state along the time process of all preset prediction steps. After that, the following steps are further included:
[0092] Step S10. If at least one of the future movement trajectories of all toppling deformable bodies or the future movement trajectories of the folds of all toppling deformable bodies does not finally reach the coincidence state, step S20 is executed.
[0093] Step S20. It is determined that the toppling deformable body does not reach the stable state within all preset prediction steps, and the toppling deformable body is marked as a deformable body that may be a future disaster.
[0094] Step S30. The coordinate enclosure areas of each enclosed differential boundary prediction coordinate set are obtained respectively.
[0095] Step S40. Taking the time process of all preset prediction steps as the horizontal axis of the rectangular coordinate system and the coordinate enclosure area as the vertical axis, a rectangular coordinate system is generated.
[0096] Step S50. The coordinate enclosure areas of each enclosed differential boundary prediction coordinate set are input into the rectangular coordinate system to obtain several enclosed differential boundary coordinate points.
[0097] Step S60. All enclosed differential boundary coordinate points are linearly fitted to obtain the increment function of the toppling deformable body.
[0098] Step S70. It is judged whether the increment function of the toppling deformable body converges. If it converges, step S80 is executed; if it does not converge, step S90 is executed.
[0099] Step S80. It is determined that the deformable body that may be a future disaster is in a convergent stable state.
[0100] Step S90. It is determined that the deformable body that may be a future disaster is in an accelerated deformation state.
[0101] Preferably, the design intention of steps S10 to S90 is to obtain the deformation rate trend of the toppling deformable body, and to know whether it is accelerated deformation or decelerated deformation through the equivalent function, so as to facilitate the adoption of subsequent measures.
[0102] Preferably, if the function converges, it indicates that the toppling deformable body may be stable in the farther future. At this time, continuous monitoring and continuous prediction are required. If direct prediction of the farther future is carried out, the prediction accuracy may decrease.
[0103] Furthermore, in step S40, a rectangular coordinate system is generated with the time process of all preset prediction steps as the horizontal axis and the area enclosed by the coordinates as the vertical axis. Thereafter, the following steps are further included:
[0104] In step S100 , the coordinate enclosed area of each coverage differential boundary prediction coordinate set is input into a rectangular coordinate system to obtain a plurality of coverage differential boundary coordinate points.
[0105] Step S200: linearly fitting all overlapping differential boundary coordinate points to obtain a fold increment function.
[0106] Step S300, determining whether the fold increment function converges, if so, executing step S400, if not, executing step S500.
[0107] Step S400: determining that the tilted deformable body is in an accelerated flow state.
[0108] Step S500: determining that the tilting deformation body is in a deceleration stable state.
[0109] Preferably, the design intention of steps S100 to S500 is to understand the motion state of the fold. At this time, it may be necessary to compare with the equivalent function of the above-mentioned tilting deformation body. If both do not converge, it means that the tilting deformation body is in a rolling state. If one of them converges, it is in a deceleration but not stopping state. If both converge, it means that it will stop and stabilize within the preset number of steps.
[0110] Furthermore, step S1, using an edge extraction algorithm to extract the overall boundary of the collapsed deformed body and the fold edge of the collapsed deformed body in each visual image, specifically includes the following steps:
[0111] In step S11, each visual image is converted into a grayscale image using the cv2.cvtColor() function of the OpenCV software package.
[0112] Step S12: Obtain all color block edges of the current grayscale image using the Canny edge detection operator.
[0113] Step S13: defining an erosion structure element of a preset pixel size.
[0114] Step S14: traverse all color block edges with the center of the eroded structure element.
[0115] Step S15: Delete all paths traversed by the eroded structure element to obtain an eroded image of the current grayscale image.
[0116] Step S16: Differentiate the current grayscale image and the current eroded image to obtain the overall boundary and the fold edge.
[0117] Further, in step S4, the enclosure differential boundary of each enclosure area differential image and the coverage differential boundary of each coverage area differential image are extracted respectively through an edge extraction algorithm, which specifically includes the following steps:
[0118] Step S41: Taking the current enclosure area differential image as the execution subject, steps S12 to S16 are repeatedly executed to obtain the enclosure differential boundary of the current enclosure area differential image.
[0119] Step S42: Taking the current coverage area differential image as the execution subject, steps S12 to S16 are repeatedly executed to obtain the coverage differential boundary of the current coverage area differential image.
[0120] Further, in step S6, a machine learning machine is used to train the elevation coordinate sets of all enclosure differential boundaries and the elevation coordinate sets of all coverage differential boundaries respectively, and several enclosure differential boundary prediction coordinate sets and several coverage differential boundary prediction coordinate sets are obtained based on several preset prediction steps, which specifically includes the following steps:
[0121] Further, in step S9, if the final coincidence state is reached, it is determined that the toppling deformation body reaches a stable state within all preset prediction steps. After that, the following steps are further included:
[0122] Step S1000: Obtain all visual images of the toppling deformation body and send them to an external visual monitoring terminal.
[0123] Step S2000: Obtain the enclosure areas of all overall boundaries and the coverage areas of all fold edges, and send them to an external visual monitoring terminal.
[0124] Step S3000: Obtain the coordinate enclosure areas of all enclosure differential boundary prediction coordinate sets and the coordinate enclosure areas of all coverage differential boundary prediction coordinate sets, and send them to an external visual monitoring terminal.
[0125] In this embodiment, the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body are respectively extracted from each visual image through an edge extraction algorithm; the enclosed area of each overall boundary and the covered area of each folded edge are respectively obtained; the adjacent enclosed areas and the adjacent covered areas are sequentially differentiated according to the time process of all preset time periods, and a differential image of the enclosed area and a differential image of the covered area are obtained based on the first-order differentiation; the enclosed differential boundary of each enclosed area differential image and the covered differential boundary of each covered area differential image are respectively extracted through the edge extraction algorithm; the elevation coordinate sets of each enclosed differential boundary and the elevation coordinate sets of each covered differential boundary are respectively obtained based on the digital elevation model of the preset area; the elevation coordinate sets of all enclosed differential boundaries and the elevation coordinate sets of all covered differential boundaries are respectively trained by a machine learning machine, and several enclosed differential boundary prediction coordinate sets and several covered differential boundary prediction coordinate sets are obtained based on several preset prediction steps; the coordinate enclosed areas of each enclosed differential boundary prediction coordinate set and the coordinate enclosed areas of each covered differential boundary prediction coordinate set are respectively obtained, and are respectively defined as a future movement trajectory of the toppling deformable body and a future movement trajectory of the folded toppling deformable body; it is judged whether all the future movement trajectories of the toppling deformable body finally reach a coincident state and whether all the future movement trajectories of the folded toppling deformable body finally reach a coincident state along the time process of all the preset prediction steps; if both finally reach a coincident state, it is determined that the toppling deformable body reaches a stable state within all the preset prediction steps. This embodiment uses vision technology to analyze two deformation characteristics of the toppling deformable body, one is the global deformation characteristic, and the other is the local deformation characteristic. At the same time, the two analyzed deformation characteristics are respectively predicted, realizing the prospect and prediction of the potential deformation characteristics of the toppling deformable body. Finally, the future deformation characteristics obtained by prediction are used to confirm the disaster trend of the toppling deformable body, making the prevention and control of the toppling deformable body forward-looking. Certain prevention and control measures can be adopted before the slope actually undergoes deformation and failure, ensuring the long-term stability of the toppling deformable body.
[0126] As Figure 2 shown, this embodiment provides an embodiment of an analysis device for a toppling deformable body. In this embodiment, the analysis device is applied to the analysis method in the above embodiment.
[0127] Specifically, the analysis device includes an overall boundary and folded edge extraction module 1, an enclosed area and covered area acquisition module 2, an enclosed area and covered area differentiation module 3, a differential boundary extraction module 4, a boundary elevation coordinate set acquisition module 5, a differential boundary prediction module 6, a future movement trajectory acquisition module 7, a future movement trajectory judgment module 8, and a stable state determination module 9 that are electrically connected in sequence.
[0128] Among them, the overall boundary and fold edge extraction module 1 is used to extract the overall boundary of the toppling deformation body and the fold edge of the toppling deformation body in each visual image respectively through an edge extraction algorithm; the enclosed area and coverage area acquisition module 2 is used to obtain the enclosed area of each overall boundary and the coverage area of each fold edge respectively; the enclosed area and coverage area difference module 3 is used to sequentially difference adjacent enclosed areas and adjacent coverage areas according to the time process of all preset time periods, and obtain an enclosed area difference image and a coverage area difference image based on one difference; the difference boundary extraction module 4 is used to extract the enclosed difference boundary of each enclosed area difference image and the coverage difference boundary of each coverage area difference image respectively through an edge extraction algorithm; the boundary elevation coordinate set acquisition module 5 is used to obtain the elevation coordinate set of each enclosed difference boundary and the elevation coordinate set of each coverage difference boundary respectively based on the digital elevation model of the preset area; the difference boundary prediction module 6 is used to train the elevation coordinate sets of all enclosed difference boundaries and the elevation coordinate sets of all coverage difference boundaries respectively through a machine learning machine, and obtain several enclosed difference boundary prediction coordinate sets and several coverage difference boundary prediction coordinate sets based on several preset prediction steps; the future movement trajectory acquisition module 7 is used to obtain the coordinate enclosed area of each enclosed difference boundary prediction coordinate set and the coordinate enclosed area of each coverage difference boundary prediction coordinate set respectively, and define them as a future movement trajectory of the toppling deformation body and a future movement trajectory of the fold of the toppling deformation body respectively; the future movement trajectory judgment module 8 is used to judge whether all future movement trajectories of the toppling deformation body finally reach a coincident state and whether all future movement trajectories of the fold of the toppling deformation body finally reach a coincident state along the time process of all preset prediction steps; the stable state determination module 9 is used to determine that the toppling deformation body reaches a stable state within all preset prediction steps if they all finally reach a coincident state.
[0129] Furthermore, the analysis device further includes a future disaster possible deformation body determination module, an enclosed difference boundary prediction coordinate set coordinate enclosed area acquisition module, a rectangular coordinate system generation module, an enclosed difference boundary coordinate point acquisition module, an enclosed difference boundary coordinate point acquisition module, a toppling deformation body increment function acquisition module, a toppling deformation body increment function judgment module, a convergence stable state determination module, and an accelerated deformation state determination module that are electrically connected in sequence; the future disaster possible deformation body determination module is electrically connected to the future movement trajectory judgment module 8.
[0130] Among them, the future disaster possible deformable body judgment module is used to determine that the toppling deformable body has not reached a stable state within all preset prediction steps if at least one of the future movement trajectories of all the toppling deformable bodies or the future movement trajectories of all the toppling deformable body folds does not eventually reach an overlapping state, and mark the toppling deformable body as a future disaster possible deformable body; the enclosed differential boundary prediction coordinate set coordinate enclosed area acquisition module is used to respectively obtain the coordinate enclosed area of each enclosed differential boundary prediction coordinate set; the rectangular coordinate system generation module is used to use the time process of all preset prediction steps as the horizontal axis of the rectangular coordinate system and the coordinate enclosed area as the vertical axis to generate into a rectangular coordinate system; the enclosed differential boundary coordinate point acquisition module is used to input the coordinate enclosed area of each enclosed differential boundary prediction coordinate set into the rectangular coordinate system to obtain a number of enclosed differential boundary coordinate points; the toppling deformation body incremental function acquisition module is used to linearly fit all the enclosed differential boundary coordinate points to obtain the toppling deformation body incremental function; the toppling deformation body incremental function judgment module is used to judge whether the toppling deformation body incremental function converges; the convergence stable state judgment module is used to judge that the future disaster possible deformable body is in a convergence stable state if it converges; the accelerated deformation state judgment module is used to judge that the future disaster possible deformable body is in an accelerated deformation state if it does not converge.
[0131] Furthermore, the analysis device also includes a coverage differential boundary coordinate point acquisition module, a fold increment function acquisition module, a fold increment function judgment module, an acceleration flow state judgment module, and a deceleration stable state judgment module, which are electrically connected in sequence; the coverage differential boundary coordinate point acquisition module is electrically connected to the rectangular coordinate system generation module.
[0132] Among them, the coverage differential boundary coordinate point acquisition module is used to input the coordinate enclosed area of each coverage differential boundary prediction coordinate set into the rectangular coordinate system to obtain a number of coverage differential boundary coordinate points; the fold increment function acquisition module is used to linearly fit all coverage differential boundary coordinate points to obtain the fold increment function; the fold increment function judgment module is used to judge whether the fold increment function converges; the acceleration flow state judgment module is used to judge that the dumping deformation body is in the acceleration flow state if it converges; the deceleration stable state judgment module is used to judge that the dumping deformation body is in the deceleration stable state if it does not converge.
[0133] Furthermore, the overall boundary and fold edge extraction module 1 specifically includes a first overall boundary and fold edge extraction unit, a second overall boundary and fold edge extraction unit, a third overall boundary and fold edge extraction unit, a fourth overall boundary and fold edge extraction unit, a fifth overall boundary and fold edge extraction unit, and a sixth overall boundary and fold edge extraction unit, which are electrically connected in sequence; the sixth overall boundary and fold edge extraction unit is electrically connected to the enclosed area and coverage area acquisition module 2.
[0134] Among them, the first overall boundary and fold edge extraction unit is used to convert each visual image into a grayscale image through the cv2.cvtCo lor() function of the OpenCV software package; the second overall boundary and fold edge extraction unit is used to obtain all color block edges of the current grayscale image through the Canny edge detection operator; the third overall boundary and fold edge extraction unit is used to define an erosion structure element of a preset pixel size; the fourth overall boundary and fold edge extraction unit is used to traverse all color block edges with the center of the erosion structure element; the fifth overall boundary and fold edge extraction unit is used to delete all paths traversed by the erosion structure element to obtain an eroded image of the current grayscale image; the sixth overall boundary and fold edge extraction unit is used to differentiate the current grayscale image and the current erosion image to obtain the overall boundary and fold edge.
[0135] Furthermore, the differential boundary extraction module 4 specifically includes a first differential boundary extraction unit and a second differential boundary extraction unit that are electrically connected in sequence; the first differential boundary extraction unit is electrically connected to the enclosed area and covered area differential module 3, the second overall boundary and fold edge extraction unit, and the sixth overall boundary and fold edge extraction unit, respectively, and the second differential boundary extraction unit is electrically connected to the boundary elevation coordinate set acquisition module 5, the second overall boundary and fold edge extraction unit, and the sixth overall boundary and fold edge extraction unit.
[0136] Among them, the first differential boundary extraction unit is used to repeatedly execute the second overall boundary and fold edge extraction unit to the sixth overall boundary and fold edge extraction unit with the current enclosed area differential image as the execution body, so as to obtain the enclosed differential boundary of the current enclosed area differential image; the second differential boundary extraction unit is used to repeatedly execute the second overall boundary and fold edge extraction unit to the sixth overall boundary and fold edge extraction unit with the current covered area differential image as the execution body, so as to obtain the covered differential boundary of the current covered area differential image.
[0137] Furthermore, the analysis device also includes a visual image acquisition and transmission module, a region acquisition and transmission module, and a differential boundary prediction coordinate set acquisition and transmission module that are electrically connected in sequence; the visual image acquisition and transmission module is electrically connected to the stable state determination module 9.
[0138] Among them, the visual image acquisition and sending module is used to acquire all visual images of the tilted deformed body and send them to the external visual monitoring end; the area acquisition and sending module is used to acquire the enclosed area of all overall boundaries and the covered area of all fold edges, and send them to the external visual monitoring end; the differential boundary prediction coordinate set acquisition and sending module is used to acquire the coordinate enclosed area of all enclosed differential boundary prediction coordinate sets and the coordinate enclosed area of all covered differential boundary prediction coordinate sets, and send them to the external visual monitoring end.
[0139] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified, and principle description parts of this embodiment, please refer to the above embodiment, and this embodiment will not be elaborated here.
[0140] In this embodiment, the edge extraction algorithm is used to extract the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body in each visual image respectively; the enclosed area of each overall boundary and the covered area of each folded edge are obtained respectively; the adjacent enclosed areas and adjacent covered areas are differenced in sequence according to the time process of all preset time periods, and a differential image of the enclosed area and a differential image of the covered area are obtained based on the first-order difference; the enclosed differential boundary of each differential image of the enclosed area and the covered differential boundary of each differential image of the covered area are extracted respectively by the edge extraction algorithm; the elevation coordinate sets of each enclosed differential boundary and the elevation coordinate sets of each covered differential boundary are obtained respectively based on the digital elevation model of the preset area; the machine learning machine is used to train the elevation coordinate sets of all enclosed differential boundaries and the elevation coordinate sets of all covered differential boundaries respectively, and a number of enclosed differential boundary prediction coordinate sets and a number of covered differential boundary prediction coordinate sets are obtained based on a number of preset prediction steps respectively; the coordinate enclosed areas of each enclosed differential boundary prediction coordinate set and the coordinate enclosed areas of each covered differential boundary prediction coordinate set are obtained respectively, and are defined as a future movement trajectory of the toppling deformable body and a future movement trajectory of the folded toppling deformable body respectively; it is judged whether all the future movement trajectories of the toppling deformable bodies finally reach the coincidence state and whether all the future movement trajectories of the folded toppling deformable bodies finally reach the coincidence state along the time process of all the preset prediction steps; if they all finally reach the coincidence state, it is determined that the toppling deformable body reaches the stable state within all the preset prediction steps. This embodiment adopts vision technology to analyze two deformation characteristics of the toppling deformable body, one is the global deformation characteristic, and the other is the local deformation characteristic. At the same time, the two analyzed deformation characteristics are predicted respectively, realizing the foresight and prediction of the potential deformation characteristics of the toppling deformable body. Finally, the disaster trend of the toppling deformable body is confirmed through the predicted future deformation characteristics, making the prevention and control of the toppling deformable body have foresight, and certain prevention and control measures can be adopted when the slope has not actually undergone deformation and failure, ensuring the long-term stability of the toppling deformable body.
[0141] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. As Figure 3 shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.
[0142] The memory 102 stores program instructions for implementing the fault detection method of an oil-immersed transformer according to any one of the above embodiments.
[0143] The processor 101 is used to execute the program instructions stored in the memory 102 for fault detection of the oil-immersed transformer.
[0144] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
[0145] Furthermore, Figure 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application. Refer to Figure 4 , the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.
[0146] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in an electrical, mechanical, or other form.
[0147] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, may exist physically alone for each unit, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation manner of the present application, and does not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present application.
Claims
1. A method for analyzing toppling deformable bodies, the toppling deformable bodies being located within a preset area, and visual images of the preset area being obtained based on a plurality of preset time periods by using small baseline interferometric synthetic aperture radar, characterized in that, The analysis method includes: Step S1: Respectively extract the overall boundary of the toppling deformable body and the folded edge of the toppling deformable body in each visual image through an edge extraction algorithm; Step S2: Respectively obtain the enclosed area of each overall boundary and the covered area of each folded edge; Step S3: Differentiate adjacent enclosed areas and adjacent covered areas in sequence according to the time process of all preset time periods, and obtain an enclosed area differential image and a covered area differential image based on the first-order difference; Step S4: Respectively extract the enclosed differential boundary of each enclosed area differential image and the covered differential boundary of each covered area differential image through the edge extraction algorithm; Step S5: Respectively obtain the elevation coordinate set of each enclosed differential boundary and the elevation coordinate set of each covered differential boundary based on the digital elevation model of the preset area; Step S6: Respectively train the elevation coordinate sets of all enclosed differential boundaries and the elevation coordinate sets of all covered differential boundaries through a machine learning machine, and obtain several enclosed differential boundary prediction coordinate sets and several covered differential boundary prediction coordinate sets based on several preset prediction steps; Step S7: Respectively obtain the coordinate enclosed area of each enclosed differential boundary prediction coordinate set and the coordinate enclosed area of each covered differential boundary prediction coordinate set, and respectively define them as a future movement trajectory of the toppling deformable body and a future movement trajectory of the fold of the toppling deformable body; Step S8: Judge whether all future movement trajectories of the toppling deformable bodies finally reach a coincident state and whether all future movement trajectories of the folds of the toppling deformable bodies finally reach a coincident state along the time process of all preset prediction steps; Step S9: If both finally reach a coincident state, it is determined that the toppling deformable body reaches a stable state within all preset prediction steps.
2. The analysis method according to claim 1, characterized in that, Step S8: Judge whether all future movement trajectories of the toppling deformable bodies finally reach a coincident state and whether all future movement trajectories of the folds of the toppling deformable bodies finally reach a coincident state along the time process of all preset prediction steps. After that, it further includes: Step S10: If at least one of all future movement trajectories of the toppling deformable bodies or all future movement trajectories of the folds of the toppling deformable bodies finally does not reach a coincident state, execute Step S20; Step S20: Determine that the toppling deformable body does not reach a stable state within all preset prediction steps, and mark the toppling deformable body as a deformable body that may be a future disaster; Step S30: Respectively obtain the coordinate enclosed area of each enclosed differential boundary prediction coordinate set; Step S40: Use the time process of all preset prediction steps as the horizontal axis of a rectangular coordinate system and the coordinate enclosed area as the vertical axis to generate a rectangular coordinate system; Step S50: Input the coordinate enclosed area of each enclosed differential boundary prediction coordinate set into the rectangular coordinate system to obtain several enclosed differential boundary coordinate points; Step S60: Linearly fit all enclosed differential boundary coordinate points to obtain an increment function of the toppling deformable body; Step S70: Judge whether the increment function of the toppling deformable body converges. If it converges, execute Step S80. If it does not converge, execute Step S90; Step S80, determine that the possible deformed body of the future disaster is in a convergent and stable state; Step S90, determine that the possible deformed body of the future disaster is in an accelerated deformation state.
3. The analysis method according to claim 2, characterized in that, Step S40, taking the time process of all preset prediction steps as the horizontal axis of the rectangular coordinate system and the enclosed area of the coordinates as the vertical axis, generate a rectangular coordinate system. After that, it further includes: Step S100, input the enclosed area of the coordinates of each set of covering differential boundary prediction coordinates into the rectangular coordinate system to obtain several covering differential boundary coordinate points; Step S200, linearly fit all the covering differential boundary coordinate points to obtain a fold increment function; Step S300, determine whether the fold increment function converges. If it converges, execute Step S400. If it does not converge, execute Step S500; Step S400, determine that the toppling deformed body is in an accelerated flow state; Step S500, determine that the toppling deformed body is in a decelerated and stable state.
4. The analysis method according to claim 1, wherein Step S1, respectively extract the overall boundary of the toppling deformed body and the folded edge of the toppling deformed body in each visual image through an edge extraction algorithm, including: Step S11, respectively convert each visual image into a grayscale image through the cv2.cvtColor() function of the OpenCV software package; Step S12, obtain all the color block edges of the current grayscale image through the Canny edge detection operator; Step S13, define a corrosion structuring element with a preset pixel size; Step S14, traverse all the color block edges with the center of the corrosion structuring element; Step S15, delete all the paths traversed by the corrosion structuring element to obtain the corrosion image of the current grayscale image; Step S16, perform a difference between the current grayscale image and the current corrosion image to obtain the overall boundary and the folded edge.
5. The analysis method according to claim 4, wherein Step S4, respectively extract the enclosed differential boundary of each enclosed area differential image and the covering differential boundary of each covering area differential image through the edge extraction algorithm, including: Step S41, repeat Steps S12 to S16 with the current enclosed area differential image as the execution subject to obtain the enclosed differential boundary of the current enclosed area differential image; Step S42, repeat Steps S12 to S16 with the current covering area differential image as the execution subject to obtain the covering differential boundary of the current covering area differential image.
6. The analysis method according to claim 1, wherein Step S9, if the coincidence state is finally reached, determine that the toppling deformed body reaches a stable state within all preset prediction steps. After that, it includes: Step S1000, obtain all the visual images of the toppling deformed body and send them to an external visual monitoring terminal; Step S2000, obtain the enclosed area of all the overall boundaries and the covering area of all the folded edges and send them to an external visual monitoring terminal; Step S3000, obtain the enclosed area of the coordinates of all the enclosed differential boundary prediction coordinate sets and the enclosed area of the coordinates of all the covering differential boundary prediction coordinate sets and send them to an external visual monitoring terminal.
7. An analysis device for a tipping deformable body, the analysis device being applied to the analysis method according to any one of claims 1 to 6, characterized in that, The analysis device includes: An overall boundary and folded edge extraction module, used to respectively extract the overall boundary of the toppling deformed body and the folded edge of the toppling deformed body in each visual image through an edge extraction algorithm; The enclosed area and covered area acquisition module is used to respectively obtain the enclosed area of each overall boundary and the covered area of each fold edge; The enclosed area and covered area difference module is used to sequentially differentiate adjacent enclosed areas and adjacent covered areas according to the time process of all preset time periods, and obtain a differential image of the enclosed area and a differential image of the covered area based on one difference; A differential boundary extraction module, configured to extract the enclosed differential boundary of each enclosed area differential image and the covered differential boundary of each covered area differential image respectively by using the edge extraction algorithm; A boundary elevation coordinate set acquisition module, configured to acquire, based on the digital elevation model of the preset area, an elevation coordinate set of each enclosing differential boundary and an elevation coordinate set of each covering differential boundary; A differential boundary prediction module is used to train all elevation coordinate sets of enclosing differential boundaries and all elevation coordinate sets of covering differential boundaries through a machine learning machine, and obtain a number of enclosing differential boundary prediction coordinate sets and a number of covering differential boundary prediction coordinate sets based on a number of preset prediction steps; The future movement trajectory acquisition module is used to respectively obtain the coordinate enclosed area of each enclosed differential boundary prediction coordinate set and the coordinate enclosed area of the covered differential boundary prediction coordinate set, and define them as a future movement trajectory of the toppling deformable body and a future movement trajectory of the toppling deformable body fold respectively; A future movement trajectory judgment module is used to judge whether the future movement trajectories of all the collapsed deformed bodies will eventually reach a coincident state, and whether the future movement trajectories of all the collapsed deformed body folds will eventually reach a coincident state along the time process of all preset prediction steps; The stable state determination module is used to determine that the tilting deformation body reaches a stable state within all preset prediction steps if the overlapping state is finally reached.
8. An electronic device, characterized in that, The invention comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the analysis method according to any one of claims 1 to 6 is implemented.
9. A storage medium, characterized in that, The storage medium stores program instructions, which, when executed by a processor, can implement the analysis method according to any one of claims 1 to 6.