Accumulation body stability analysis method and system under surge impact condition

Abstract

The invention discloses an accumulation body stability analysis method and system under a surge impact condition, and relates to the technical field of disaster prevention and control, and the method identifies the action range of surge impact through computer vision, and learns the action range through machine learning to prevent data from exceeding the current range and being missed. Collecting points are reasonably arranged in the range, data collected by the collecting points are analyzed, spatial and temporal distribution of impact loads acting on the accumulation body by the landslide surge is determined, the impact loads are converted into equivalent static force through the momentum theorem, and finally the safety coefficient is calculated. Meanwhile, the landslide surge impact load value required during stability analysis is determined by utilizing a pseudo-static method, so that the problem that the stability analysis is inconvenient to carry out on the landslide surge impact load value obtained by experimental observation can be effectively solved; a simple and accurate calculation method is provided for stable analysis of the accumulation body under the action of the surge impact load.

Description

Technical Field

[0001] The present application relates to the field of disaster prevention and control technology, and in particular to a method and system for analyzing the stability of a pile under surge impact conditions. Background Art

[0002] Due to the complex and extremely unstable geological conditions of the high slopes in mountainous reservoir areas, they are prone to become unstable under the influence of adverse external factors and slide rapidly into the reservoir, forming landslide surges that pose serious risks to the reservoir coast and downstream dams.

[0003] Due to complex geological conditions and frequent groundwater fluctuations in high mountain valleys, unstable accumulations are often found near hydropower station dams and reservoir banks. These accumulations are large in scale, with complex slope material composition and evolutionary mechanisms. While relatively stable in their natural state, they become less stable under adverse external factors such as surge loads. Once unstable, the resulting surges can threaten the safety of water-retaining structures and hydraulic gates, with serious consequences. Therefore, further research is needed to assess the stability of accumulations near dam banks.

[0004] Currently, research on landslide surges has mostly focused on the generation process of landslide surges, their superposition during propagation, and their attenuation patterns. However, there is limited research on the impact of landslide surges on dam deposits. Accumulation stability assessment under landslide surges and the development of targeted prevention and control strategies are of great scientific and engineering significance. Currently, the stability of dam deposits is primarily analyzed through geomechanical analysis, geostatistical analysis, and finite element analysis. These methods rely heavily on subjective experience and prior knowledge, and place high demands on the quantity and quality of data. However, the inclusion of subjective experience and prior knowledge inevitably leads to prediction errors, resulting in low accuracy in subsequent dam stability analysis. Summary of the Invention

[0005] The main purpose of this application is to provide a method and system for analyzing the stability of a pile under surge impact conditions, so as to solve the problem in the prior art that the stability analysis of the pile is not accurate due to the substitution of human subjective experience and prior knowledge.

[0006] In order to achieve the above objectives, this application provides the following technical solutions: A method for analyzing the stability of an accumulation body under surge impact conditions is provided. The method is applied to an accumulation body subjected to landslide surge impact in a predetermined area. The method comprises: Step S1, obtaining the horizontal impact range and vertical impact range of the surge impact through computer vision based on a plurality of shooting time intervals; Step S2, predicting the future horizontal impact range and vertical impact range of the landslide surge impact through all horizontal impact ranges and all vertical impact ranges based on a machine learning machine; Step S3, obtaining an axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the pile; Step S4, evenly arranging a plurality of impact load collection points at a preset array density on the above-water portion, the water surface, and the underwater portion of the three-dimensional arrangement range, and having the impact load collection points at the edge of the three-dimensional arrangement range; Step S5, acquiring impact load data of the accumulation body through all impact load collection points based on a plurality of collection time intervals, wherein the impact load data includes impact load force and impact load action duration; Step S6, converting all impact load data into impact load velocity based on the mass of the stack by using the momentum theorem; Step S7, obtaining an impact acceleration based on the impact load velocity of the adjacent impact load action duration, and converting the current impact acceleration into an equivalent static force through the mass of the stack; Step S8, respectively substituting each equivalent static force into the equilibrium equation of the limit equilibrium method to obtain several safety factors along the time series; Step S9: defining all safety factors lower than a critical value and corresponding time stamps as instability risk data of the pile.

[0007] As a further improvement of the present application, step S9 defines all safety factors below a critical value and corresponding timestamps as instability risk data of the pile, and then includes: Step S10, obtaining the first safety factor exceeding the critical value among all safety factors and marking it as the instability starting point; Step S20, starting from the instability starting point, obtaining the duration of the safety factor of the subsequent time series exceeding the critical value; Step S30: If the duration ends within all the acquisition time intervals, it is determined that the accumulation body has stabilized again after being unstable, forming an accumulation body with a new structure; Step S40: If the duration does not end within all the collection time intervals, it is determined that the accumulation body is completely unstable.

[0008] As a further improvement of the present application, in step S40, if the duration does not end within all the collection time intervals, it is determined that the accumulation body is completely unstable, and then the following steps are included: Step S100: if a new structure of the deposited body is formed, a deformation signal of the deposited body is generated; Step S200, sending the stack deformation signal to an external monitoring terminal; Step S300: If it is determined that the deposit is completely unstable, a deposit complete instability signal is generated; Step S400: sending a signal indicating that the stack is completely unstable to an external monitoring terminal.

[0009] As a further improvement of the present application, step S9 defines all safety factors below a critical value and corresponding timestamps as instability risk data of the pile, and then includes: Step S100, packaging all instability risk data into a data packet; Step S200: Expand the data packet in time sequence on an external visualization terminal to obtain an instability risk report.

[0010] As a further improvement of the present application, step S1, obtaining the horizontal impact range and the vertical impact range of the surge impact through computer vision based on a plurality of shooting time intervals, includes: Step S11, capturing a plurality of overhead images from a bird's-eye view of the surge impact based on a plurality of shooting time intervals; Step S12, capturing a plurality of side-view images from a side-view perspective of the surge impact based on a plurality of shooting time intervals; Step S13, training an initial detection model of a target detection algorithm using a plurality of preset overhead swell images to obtain an overhead swell detection model; Step S14, obtaining a surge overhead image detection frame of the surge impact in each overhead image using the overhead surge detection model, and defining a surge overhead image detection frame as a horizontal impact range; Step S15, training the initial detection model using a plurality of preset side surge images to obtain a side surge detection model; Step S16: obtaining a surge side view image detection frame of the surge impact in each side view image through the side surge detection model, and defining a surge side view image detection frame as a vertical impact range.

[0011] As a further improvement of the present application, step S3, obtaining an axis-aligned bounding box consisting of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the pile, includes: Step S31: scaling the horizontal influence range and the vertical influence range corresponding to the maximum area to the same scale, and defining them as the horizontal maximum influence range and the vertical maximum influence range, respectively; Step S32: Mapping the horizontal maximum influence range and the vertical maximum influence range to the preset area through a homography matrix to obtain the coordinates of four corners of the horizontal maximum influence range and the coordinates of four corners of the vertical maximum influence range respectively; Step S33: Obtain an axis-aligned bounding box of eight corner coordinates, where the axis-aligned bounding box is the three-dimensional arrangement range.

[0012] As a further improvement of the present application, the equilibrium equation in step S8 is represented by formula (1): (1); in, is the safety factor, is the effective cohesion of the stack, is the sliding surface length of the deposit, is the bottom normal force of the pile, is the pore water pressure of the deposit, is the effective internal friction angle of the pile, is the deadweight of the pile, is the angle between the equivalent static force and the sliding surface of the pile, is the equivalent static force.

[0013] In order to achieve the above objectives, this application also provides the following technical solutions: A system for analyzing the stability of an accumulation body under surge impact conditions, wherein the system is applied to the above-mentioned accumulation body stability analysis method, and the system comprises: A surge impact range acquisition module is used to acquire the horizontal impact range and vertical impact range of the surge impact through computer vision based on a number of shooting time intervals; A surge impact range prediction module is used to predict the future horizontal impact range and vertical impact range of the landslide surge impact through all horizontal impact ranges and all vertical impact ranges based on a machine learning machine; A three-dimensional arrangement range definition module is used to obtain an axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the accumulation body; An impact load collection point arrangement module is configured to evenly arrange a plurality of impact load collection points at a preset array density in the above-water portion, the water surface, and the underwater portion of the three-dimensional arrangement range, with the impact load collection points being located at the edges of the three-dimensional arrangement range; An impact load data acquisition module, configured to acquire impact load data of the accumulation body through all impact load acquisition points based on a plurality of acquisition time intervals, wherein the impact load data includes impact load force and impact load action duration; An impact load velocity conversion module, configured to convert all impact load data into impact load velocity by using the momentum theorem based on the mass of the accumulation body; An equivalent static force conversion module is used to obtain an impact acceleration based on the impact load velocity of the adjacent impact load action duration, and convert the current impact acceleration into an equivalent static force through the mass of the accumulation body; Safety factor calculation module, used to substitute each equivalent static force into the equilibrium equation of the limit equilibrium method and obtain several safety factors along the time series; The instability risk data definition module is used to define all safety factors below a critical value and corresponding time stamps as instability risk data of the accumulation body.

[0014] In order to achieve the above objectives, this application also provides the following technical solutions: An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned method for analyzing the stability of a deposit is implemented.

[0015] In order to achieve the above objectives, this application also provides the following technical solutions: A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned method for analyzing the stability of a deposit.

[0016] The present application obtains the horizontal impact range and vertical impact range of surge impact through computer vision based on several shooting time intervals; predicts the horizontal impact range and vertical impact range of landslide surge impact in the future through all horizontal impact ranges and all vertical impact ranges based on machine learning; obtains the axis-aligned bounding box composed of the maximum area in all horizontal impact ranges and all vertical impact ranges as the three-dimensional arrangement range of impact load collection points of the accumulation body; uniformly arranges a number of impact load collection points in the above-water part, water surface and underwater part of the three-dimensional arrangement range with a preset array density, and the edge of the three-dimensional arrangement range has impact load collection points; based on The impact load data of the accumulation body are obtained through all impact load collection points at several collection time intervals. The impact load data includes the impact load force and the impact load duration. Based on the mass of the accumulation body, all impact load data are converted into impact load velocity through the momentum theorem. An impact acceleration is obtained based on the impact load velocity of adjacent impact load durations, and the current impact acceleration is converted into an equivalent static force through the mass of the accumulation body. Each equivalent static force is substituted into the equilibrium equation of the limit equilibrium method respectively, and several safety factors are obtained along the time series. All safety factors below the critical value and the corresponding timestamps are defined as the instability risk data of the accumulation body. This application uses computer vision to identify the scope of surge impact, and at the same time uses machine learning to learn the scope to prevent data from exceeding the current scope and being missed, then reasonably arranges collection points within the scope and analyzes the data collected by the collection points, determines the spatiotemporal distribution of the impact load of the landslide surge on the accumulation body, converts the impact load into equivalent static force through the momentum theorem, and finally calculates the safety factor. At the same time, this application uses the pseudo-static method to determine the landslide surge impact load value required for stability analysis, which can effectively solve the problem that the landslide surge impact load value obtained from experimental observations is not convenient for stability analysis, and proposes a simple and accurate calculation method for the stability analysis of the accumulation body under the action of surge impact load. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of the steps of an embodiment of a method for analyzing the stability of a pile under surge impact conditions of the present application; Figure 2 This is a functional module diagram of an embodiment of a system for analyzing the stability of a pile under surge impact conditions of the present application; Figure 3 This is a schematic structural diagram of an embodiment of the electronic device of the present application; Figure 4 This is a structural diagram of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to such process, method, product, or apparatus.

[0020] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] like Figure 1 As shown, this embodiment provides an embodiment of a method for analyzing the stability of an accumulation body under surge impact conditions. In this embodiment, the method for analyzing the stability of an accumulation body is applied to an accumulation body subjected to landslide surge impact in a preset area.

[0022] Preferably, the accumulation body is more common near the dam bank of the hydropower station. The accumulation body near the dam bank refers to the Quaternary loose accumulation geological body formed by geological action on the slope of the reservoir area near the dam site of the hydropower station. This type of accumulation body is usually composed of a mixture of crushed stone soil, pebbles, weathered rock debris, etc., and some may contain bedrock components such as sandy slate. The structural density is uneven, and it is often loose to medium dense.

[0023] Preferably, the accumulation body of this type is mainly derived from the accumulation after the slope deformation and destruction of landslides, collapses and the like, may undergo long-term creep deformation process, and is partially related to terrace accumulation, aeolian deposition and the like, and has a scale of hundreds of thousands of cubic meters, often presents a critical stability or creep state, and has a direct impact on the safety of reservoir construction and operation. The reservoir water level fluctuation will change the seepage field, and the rainfall infiltration will intensify the deformation risk.

[0024] Specifically, the accumulation body stability analysis method comprises the following steps: Step S1, the horizontal and vertical impact ranges of the surge impact are obtained by computer vision based on a plurality of shooting time intervals.

[0025] Preferably, since the surge impact is a second-level action, the shooting time interval of the impact range can be set to 1 second, and if the impact action is to be refined, it can be set to 0.1 second or even 0.01 second.

[0026] Step S2, the machine learning machine predicts the future horizontal and vertical impact ranges of the landslide surge impact based on all the horizontal and vertical impact ranges.

[0027] Preferably, all the impact ranges can be trained and learned by a neural network model. By dividing the two impact ranges into a training set, a validation set and a test set respectively, the current training set is trained by the neural network model, and the weights and biases of the neural network model are updated according to the loss function of the training result and the current validation set by the back propagation algorithm. Repeat the back propagation for several times until the loss function reaches the minimum value, that is, the prediction model is obtained, and the test set is substituted into the prediction model to obtain the prediction data.

[0028] It is worth noting that the horizontal and vertical impact ranges predicted by the present embodiment are not separately named, and are intended to facilitate subsequent unified search for the three-dimensional arrangement range. The future horizontal and vertical impact ranges are essentially the same as the real-time horizontal and vertical impact ranges, only the time sequence is different.

[0029] Step S3, the axis-aligned bounding box composed of the maximum area in all the horizontal and vertical impact ranges is obtained as the three-dimensional arrangement range of the impact load collection points of the accumulation body.

[0030] Preferably, the axis-aligned bounding box is also called an AABB box, and the edges of the box are aligned with the normal axes.

[0031] Step S4, a plurality of impact load collection points are uniformly arranged in a preset array density on the water part, the water surface and the underwater part of the three-dimensional arrangement range, and the edge of the three-dimensional arrangement range has an impact load collection point.

[0032] Preferably, the horizontal spacing of the impact load collection points is 1.0 m, the vertical spacing is usually 2-5 m, and there are no less than 3 measuring points.

[0033] Step S5: acquiring impact load data of the accumulation body through all impact load collection points based on a plurality of collection time intervals. The impact load data includes impact load force and impact load action duration.

[0034] Preferably, a high-precision dynamic force sensor can be used to directly acquire the above data.

[0035] Step S6: converting all impact load data into impact load velocity based on the mass of the accumulation body through the momentum theorem.

[0036] Preferably, the momentum theorem is Ft=mv, where F is the impact load force, t is the duration of the impact load, m is the deadweight of the pile, and v is the impact load velocity.

[0037] It is worth noting that the symbols in the formula here are for explanation of the principle and have no interchangeable meanings with other symbols in this embodiment.

[0038] Step S7: obtaining an impact acceleration based on the impact load velocity of the adjacent impact load action duration, and converting the current impact acceleration into an equivalent static force through the mass of the accumulation body.

[0039] Preferably, the impact acceleration is calculated by a=(v1-v2) / (t1-t2), wherein v1 and v2 are impact load velocities of adjacent impact load action times, and t1 and t2 are adjacent impact load action times.

[0040] Preferably, the equivalent static force is obtained by F impact =ma conversion, where f is the equivalent static force, m is the deadweight of the pile, and a is the impact acceleration.

[0041] In step S8, each equivalent static force is substituted into the equilibrium equation of the limit equilibrium method to obtain several safety factors along the time series.

[0042] Furthermore, the equilibrium equation in step S8 is represented by formula (1): (1).

[0043] in, is the safety factor, is the effective cohesion of the accumulation body, is the sliding surface length of the accumulation body, is the normal force at the bottom of the pile, is the pore water pressure of the accumulation body, is the effective internal friction angle of the deposit, is the deadweight of the pile, is the angle between the equivalent static force and the sliding surface of the accumulation body, is the equivalent static force.

[0044] Preferably, the effective cohesion is measured by a direct shear test or a triaxial shear test. The sample must be kept in a saturated state and the drainage conditions must be controlled. The cohesion can be indirectly inferred from the unconfined compressive strength test (c = unconfined compressive strength / 2). Alternatively, the undrained shear strength of soft soil can be measured using a cross-plate shear apparatus and corrected to the effective stress parameter based on the pore water pressure data.

[0045] Preferably, the length of the sliding surface is determined by drilling, trenching or geological radar to detect the potential sliding surface position and extension range, and the development trend of the sliding surface is determined by combining the stress distribution characteristics of the slope (such as the shear stress concentration zone at the slope foot and the tension zone at the slope top).

[0046] Preferably, the bottom normal force is calculated based on the self-weight stress distribution and slope shape (slope height, slope angle), and the influence of horizontal residual stress on the deflection of the principal stress trace needs to be considered.

[0047] Preferably, the pore water pressure is measured by installing a pore water pressure gauge (such as a vibrating wire sensor). Attention should be paid to the effect of dynamic water pressure on erosion and quicksand phenomena, and it is necessary to distinguish between static water pressure and seepage pressure.

[0048] Preferably, the effective internal friction angle and cohesion are obtained simultaneously through direct shear or triaxial tests. Drainage conditions need to be controlled to eliminate the influence of pore water pressure. For coarse-grained soils, a large shear tester can be used to reduce size effect errors.

[0049] Preferably, the bulk density is determined by soil classification (gravel soil, clay soil, etc.) and the total weight is calculated based on the geometric dimensions. For special soils (such as collapsible loess and expansive soil), the effect of changes in moisture content on the bulk density needs to be considered.

[0050] Step S9: defining all safety factors below the critical value and the corresponding timestamps as instability risk data of the accumulation body.

[0051] Preferably, the safety factor under normal working conditions is generally set to ≥1.3, that is, the critical value is 1.3.

[0052] Furthermore, in step S9, all safety factors below the critical value and the corresponding timestamps are defined as instability risk data of the accumulation body, and then the following steps are included: Step S10: Obtain the first safety factor below the critical value among all safety factors and mark it as the instability starting point.

[0053] Step S20 , starting from the instability starting point, obtain the duration of the safety factor of the subsequent time series being lower than the critical value.

[0054] In step S30, if the duration ends within all the acquisition time intervals, it is determined that the accumulation body has stabilized again after being unstable, and an accumulation body with a new structure is formed.

[0055] Step S40: If the duration does not end within all the collection time intervals, it is determined that the accumulation body is completely unstable.

[0056] Furthermore, in step S40, if the duration does not end within all the collection time intervals, it is determined that the pile is completely unstable, and then the following steps are included: In step S100 , if a new structured deposit is formed, a deposit deformation signal is generated.

[0057] Step S200: sending a stack deformation signal to an external monitoring terminal.

[0058] In step S300 , if it is determined that the deposit is completely unstable, a deposit completely unstable signal is generated.

[0059] Step S400: sending a signal indicating that the stack is completely unstable to an external monitoring terminal.

[0060] Furthermore, in step S9, all safety factors below the critical value and the corresponding timestamps are defined as instability risk data of the accumulation body, and then the following steps are included: Step S100: Pack all instability risk data into a data packet.

[0061] Step S200: Expand the data packets according to the time sequence on the external visualization terminal to obtain an instability risk report.

[0062] Furthermore, step S1, based on a plurality of shooting time intervals, obtains the horizontal impact range and the vertical impact range of the surge impact through computer vision, including: Step S11 : capturing a plurality of overhead images from a bird's-eye view of the surge impact at a plurality of shooting time intervals.

[0063] Step S12: capturing a plurality of side-view images from a side-view perspective of the surge impact based on a plurality of shooting time intervals.

[0064] Step S13: training an initial detection model of a target detection algorithm using a plurality of preset overhead swell images to obtain an overhead swell detection model.

[0065] Preferably, the target detection algorithm can be set to yolo V5.

[0066] Step S14: obtaining a surge overhead image detection frame of surge impact in each overhead image through the overhead surge detection model, and defining a surge overhead image detection frame as a horizontal impact range.

[0067] Step S15 , training an initial detection model using a number of preset side surge images to obtain a side surge detection model.

[0068] Step S16: obtaining a surge side view image detection frame of each side view image where the surge impact occurs through the side view surge detection model, and defining a surge side view image detection frame as a vertical impact range.

[0069] Furthermore, step S3, obtaining an axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the accumulation body, including: In step S31 , the horizontal influence range and the vertical influence range corresponding to the maximum area are scaled to the same scale, and are defined as the horizontal maximum influence range and the vertical maximum influence range, respectively.

[0070] Step S32 : Mapping the horizontal maximum influence range and the vertical maximum influence range to a preset area through a homography matrix to obtain the coordinates of the four corners of the horizontal maximum influence range and the coordinates of the four corners of the vertical maximum influence range respectively.

[0071] Preferably, the homography matrix needs to be combined with radar data from the same shooting point. By mapping the radar data into the image, the true position of the detection frame can be known. Since the shooting angles are all normal, the detection frame will not produce a perspective effect.

[0072] Step S33: Obtain the axis-aligned bounding box of the eight corner coordinates. The axis-aligned bounding box is the three-dimensional arrangement range.

[0073] The embodiment obtains the horizontal impact range and the vertical impact range of the surge wave impact through computer vision based on a plurality of shooting time intervals; predicts the future horizontal impact range and the vertical impact range of the landslide surge wave impact through all the horizontal impact ranges and all the vertical impact ranges based on a machine learning machine; obtains an axis-aligned bounding box composed of the maximum area in all the horizontal impact ranges and all the vertical impact ranges as a three-dimensional arrangement range of impact load collection points of the accumulation body; evenly arranges a plurality of impact load collection points on the water part, the water surface, and the underwater part of the three-dimensional arrangement range at a preset array density, and the edge of the three-dimensional arrangement range has an impact load collection point; obtains the impact load data of the accumulation body through all the impact load collection points based on a plurality of collection time intervals, and the impact load data includes impact load force and impact load action time length; converts all the impact load data into impact load velocity through the momentum theorem based on the mass of the accumulation body; obtains an impact acceleration based on the impact load velocity of adjacent impact load action time lengths, and converts the current impact acceleration into an equivalent static force through the mass of the accumulation body; substitutes each equivalent static force into the balance equation of the limit equilibrium method respectively, and obtains a plurality of safety factors along the time sequence; defines all the safety factors lower than the critical value and the corresponding time stamp as the instability risk data of the accumulation body. The embodiment identifies the action range of the surge wave impact through computer vision, simultaneously learns the action range through machine learning to prevent data from being missed due to exceeding the current range, reasonably arranges the collection points in the range, and analyzes the data collected through the collection points to determine the spatiotemporal distribution of the impact load of the landslide surge wave on the accumulation body, converts the impact load into an equivalent static force through the momentum theorem, and finally calculates the safety factor. Meanwhile, the embodiment determines the landslide surge wave impact load value required for stability analysis by using the pseudo-static method, which can effectively solve the problem that the landslide surge wave impact load value obtained through experimental observation is inconvenient for stability analysis, and provides a simple and accurate calculation method for stability analysis of the accumulation body under the action of the surge wave impact load.

[0074] As shown in Figure 2 , the embodiment provides a landslide surge wave impact condition accumulation body stability analysis system, which is applied to the accumulation body stability analysis method as described above.

[0075] Preferably, the accumulation body stability analysis system comprises, in sequence, a surge wave impact influence range obtaining module 1, a surge wave impact influence range predicting module 2, a three-dimensional arrangement range defining module 3, an impact load collection point arranging module 4, an impact load data collecting module 5, an impact load velocity converting module 6, an equivalent static force converting module 7, a safety factor calculating module 8, and an instability risk data defining module 9.

[0076] Among them, the surge impact impact range acquisition module 1 is used to obtain the horizontal impact range and vertical impact range of the surge impact through computer vision based on several shooting time intervals; the surge impact impact range prediction module 2 is used to predict the future horizontal impact range and vertical impact range of the landslide surge impact through all horizontal impact ranges and all vertical impact ranges based on the machine learning machine; the three-dimensional layout range definition module 3 is used to obtain the axis-aligned bounding box composed of the maximum area in all horizontal impact ranges and all vertical impact ranges as the three-dimensional layout range of the impact load collection point of the accumulation body; the impact load collection point arrangement module 4 is used to evenly arrange a number of impact load collection points in the above-water part, water surface and underwater part of the three-dimensional layout range with a preset array density, and the edge of the three-dimensional layout range has impact load collection points; impact load The data acquisition module 5 is used to obtain the impact load data of the accumulation body through all impact load collection points based on several collection time intervals. The impact load data includes the impact load force and the duration of the impact load; the impact load velocity conversion module 6 is used to convert all impact load data into impact load velocity through the momentum theorem based on the mass of the accumulation body; the equivalent static force conversion module 7 is used to obtain an impact acceleration based on the impact load velocity of the adjacent impact load duration, and convert the current impact acceleration into an equivalent static force through the mass of the accumulation body; the safety factor calculation module 8 is used to substitute each equivalent static force into the equilibrium equation of the limit equilibrium method respectively, and obtain several safety factors along the time series; the instability risk data definition module 9 is used to define all safety factors below the critical value and the corresponding timestamps as instability risk data of the accumulation body.

[0077] Furthermore, the accumulation stability analysis system also includes an instability starting point acquisition module, an instability duration acquisition module, a new structure accumulation determination module, and an accumulation complete instability determination module, which are electrically connected in sequence; the instability starting point acquisition module is electrically connected to the instability risk data definition module 9.

[0078] Among them, the instability starting point acquisition module is used to obtain the first safety factor below the critical value among all safety factors and mark it as the instability starting point; the instability duration acquisition module is used to obtain the duration of the safety factor of the subsequent time series below the critical value starting from the instability starting point; the new structure accumulation body judgment module is used to judge that the accumulation body has become unstable and then stabilized again to form a new structure accumulation body if the duration ends within all acquisition time intervals; the accumulation body complete instability judgment module is used to judge that the accumulation body is completely unstable if the duration does not end within all acquisition time intervals.

[0079] Furthermore, the accumulation body stability analysis system also includes an accumulation body deformation signal generating module, an accumulation body deformation signal sending module, an accumulation body complete instability signal generating module, and an accumulation body complete instability signal sending module, which are electrically connected in sequence; the accumulation body deformation signal generating module is electrically connected to the accumulation body complete instability judgment module.

[0080] Among them, the stacking body deformation signal generating module is used to generate a stacking body deformation signal if a new structure of the stacking body is formed; the stacking body deformation signal sending module is used to send the stacking body deformation signal to the external monitoring end; the stacking body complete instability signal generating module is used to generate a stacking body complete instability signal if it is determined that the stacking body is completely unstable; the stacking body complete instability signal sending module is used to send the stacking body complete instability signal to the external monitoring end.

[0081] Furthermore, the accumulation stability analysis system further includes an instability risk data packaging module and an instability risk data visualization module electrically connected in sequence; the instability risk data packaging module is electrically connected to the instability risk data definition module 9.

[0082] Among them, the instability risk data packaging module is used to package all instability risk data into data packets; the instability risk data visualization module is used to expand the data packets according to the time series on the external visualization terminal to obtain the instability risk report.

[0083] Furthermore, the surge impact range acquisition module 1 specifically includes a first surge impact range acquisition unit, a second surge impact range acquisition unit, a third surge impact range acquisition unit, a fourth surge impact range acquisition unit, a fifth surge impact range acquisition unit, and a sixth surge impact range acquisition unit, which are electrically connected in sequence; the sixth surge impact range acquisition unit is electrically connected to the surge impact range prediction module 2.

[0084] Among them, the first surge impact influence range acquisition unit is used to shoot a number of overhead images through the overhead perspective of the surge impact based on a number of shooting time intervals; the second surge impact influence range acquisition unit is used to shoot a number of side images through the side perspective of the surge impact based on a number of shooting time intervals; the third surge impact influence range acquisition unit is used to train the initial detection model of the target detection algorithm through a number of preset overhead surge images to obtain the overhead surge detection model; the fourth surge impact influence range acquisition unit is used to obtain the surge overhead image detection frame of the surge impact in each overhead image through the overhead surge detection model, and define a surge overhead image detection frame as a horizontal influence range; the fifth surge impact influence range acquisition unit is used to train the initial detection model through a number of preset side surge images to obtain the side surge detection model; the sixth surge impact influence range acquisition unit is used to obtain the surge side image detection frame of the surge impact in each side image through the side surge detection model, and define a surge side image detection frame as a vertical influence range.

[0085] Furthermore, the three-dimensional arrangement range definition module 3 specifically includes a first three-dimensional arrangement range definition unit, a second three-dimensional arrangement range definition unit, and a third three-dimensional arrangement range definition unit that are electrically connected in sequence; the first three-dimensional arrangement range definition unit is electrically connected to the surge impact influence range prediction module 2, and the third three-dimensional arrangement range definition unit is electrically connected to the impact load collection point arrangement module 4.

[0086] Among them, the first three-dimensional arrangement range definition unit is used to scale the horizontal influence range and vertical influence range corresponding to the maximum area to the same scale, and define them as the horizontal maximum influence range and the vertical maximum influence range respectively; the second three-dimensional arrangement range definition unit is used to map the horizontal maximum influence range and the vertical maximum influence range to a preset area through a homography matrix, and obtain the four corner coordinates of the horizontal maximum influence range and the four corner coordinates of the vertical maximum influence range respectively; the third three-dimensional arrangement range definition unit is used to obtain the axis-aligned bounding box of the eight corner coordinates, and the axis-aligned bounding box is the three-dimensional arrangement range.

[0087] Furthermore, the safety factor calculation module 8 is equipped with the equilibrium equation represented by formula (1): (1).

[0088] in, is the safety factor, is the effective cohesion of the accumulation body, is the sliding surface length of the accumulation body, is the normal force at the bottom of the pile, is the pore water pressure of the accumulation body, is the effective internal friction angle of the deposit, is the deadweight of the pile, is the angle between the equivalent static force and the sliding surface of the accumulation body, is the equivalent static force.

[0089] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and will not be repeated in this embodiment.

[0090] This embodiment obtains the horizontal influence range and vertical influence range of the surge impact through computer vision based on several shooting time intervals; predicts the horizontal influence range and vertical influence range of the landslide surge impact in the future through all horizontal influence ranges and all vertical influence ranges based on the machine learning machine; obtains the axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection point of the accumulation body; uniformly arranges a number of impact load collection points in the above-water part, water surface and underwater part of the three-dimensional arrangement range with a preset array density, and the edge of the three-dimensional arrangement range has impact load collection points; based At several collection time intervals, the impact load data of the accumulation body is obtained through all impact load collection points. The impact load data includes the impact load force and the impact load duration. Based on the mass of the accumulation body, all impact load data are converted into impact load velocity through the momentum theorem. An impact acceleration is obtained based on the impact load velocity of adjacent impact load durations, and the current impact acceleration is converted into an equivalent static force through the mass of the accumulation body. Each equivalent static force is substituted into the equilibrium equation of the limit equilibrium method, and several safety factors are obtained along the time series. All safety factors below the critical value and the corresponding timestamps are defined as the instability risk data of the accumulation body. This embodiment uses computer vision to identify the scope of surge impact, and at the same time uses machine learning to learn the scope to prevent data from exceeding the current scope and being missed. Then, collection points are reasonably arranged within the scope and the data collected by the collection points are analyzed to determine the spatiotemporal distribution of the impact load of the landslide surge on the accumulation body. The impact load is converted into equivalent static force through the momentum theorem, and finally the safety factor is calculated. At the same time, this embodiment uses the pseudo-static method to determine the landslide surge impact load value required for stability analysis, which can effectively solve the problem that the landslide surge impact load value obtained from experimental observations is not convenient for stability analysis, and proposes a simple and accurate calculation method for the stability analysis of the accumulation body under the action of surge impact load.

[0091] like Figure 3 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0092] The memory 102 stores program instructions for implementing the method for analyzing the stability of a pile under surge impact conditions according to any of the above embodiments.

[0093] The processor 101 is configured to execute program instructions stored in the memory 102 to perform a stability analysis of a pile under surge impact conditions.

[0094] Processor 101 may also be referred to as a CPU (Central Processing Unit). Processor 101 may be an integrated circuit chip with data processing capabilities. Processor 101 may also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor or any conventional processor.

[0095] Furthermore, Figure 4 This is a schematic diagram of the structure of a storage medium in an embodiment of the present application. The storage medium 11 in the embodiment of the present application stores program instructions 111 that can implement all of the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, server, mobile phone, and tablet.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of units is only a logical function division. 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 is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0097] In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0098] The above detailed description of the specific embodiments of the present application is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions made to the present application are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A method for analyzing the stability of an accumulation body under surge impact conditions, wherein the method is applied to an accumulation body subjected to landslide surge impact in a predetermined area, and is characterized in that: The method for analyzing the stability of the deposited body comprises: Step S1, obtaining the horizontal impact range and vertical impact range of the surge impact through computer vision based on a plurality of shooting time intervals; Step S2, predicting the future horizontal impact range and vertical impact range of the landslide surge impact through all horizontal impact ranges and all vertical impact ranges based on a machine learning machine; Step S3, obtaining an axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the pile; Step S4, evenly arranging a plurality of impact load collection points at a preset array density on the above-water portion, the water surface, and the underwater portion of the three-dimensional arrangement range, and having the impact load collection points at the edge of the three-dimensional arrangement range; Step S5, acquiring impact load data of the accumulation body through all impact load collection points based on a plurality of collection time intervals, wherein the impact load data includes impact load force and impact load action duration; Step S6, converting all impact load data into impact load velocity based on the mass of the stack by using the momentum theorem; Step S7, obtaining an impact acceleration based on the impact load velocity of the adjacent impact load action duration, and converting the current impact acceleration into an equivalent static force through the mass of the stack; Step S8, respectively substituting each equivalent static force into the equilibrium equation of the limit equilibrium method to obtain several safety factors along the time series; Step S9: defining all safety factors lower than a critical value and corresponding time stamps as instability risk data of the pile.

2. The method for analyzing the stability of a deposit according to claim 1, wherein: Step S9, defining all safety factors below a critical value and corresponding timestamps as instability risk data of the pile, and then including: Step S10, obtaining the first safety factor exceeding the critical value among all safety factors and marking it as the instability starting point; Step S20, starting from the instability starting point, obtaining the duration of the safety factor of the subsequent time series exceeding the critical value; Step S30: If the duration ends within all the acquisition time intervals, it is determined that the accumulation body has stabilized again after being unstable, forming an accumulation body with a new structure; Step S40: If the duration does not end within all the collection time intervals, it is determined that the accumulation body is completely unstable.

3. The method for analyzing the stability of a deposit according to claim 2, wherein: Step S40: If the duration does not end within all the collection time intervals, it is determined that the deposit is completely unstable. Then, the following steps are performed: Step S100: if a new structure of the deposited body is formed, a deformation signal of the deposited body is generated; Step S200, sending the stack deformation signal to an external monitoring terminal; Step S300: If it is determined that the deposit is completely unstable, a deposit complete instability signal is generated; Step S400: sending a signal indicating that the stack is completely unstable to an external monitoring terminal.

4. The method for analyzing the stability of a deposit according to claim 1, wherein: Step S9, defining all safety factors below a critical value and corresponding timestamps as instability risk data of the pile, and then including: Step S100, packaging all instability risk data into a data packet; Step S200: Expand the data packet in time sequence on an external visualization terminal to obtain an instability risk report.

5. The method for analyzing the stability of a deposit according to claim 1, wherein: Step S1, obtaining the horizontal impact range and vertical impact range of the surge impact through computer vision based on a plurality of shooting time intervals, including: Step S11, capturing a plurality of overhead images from a bird's-eye view of the surge impact based on a plurality of shooting time intervals; Step S12, capturing a plurality of side-view images from a side-view perspective of the surge impact based on a plurality of shooting time intervals; Step S13, training an initial detection model of a target detection algorithm using a plurality of preset overhead swell images to obtain an overhead swell detection model; Step S14, obtaining a surge overhead image detection frame of the surge impact in each overhead image using the overhead surge detection model, and defining a surge overhead image detection frame as a horizontal impact range; Step S15, training the initial detection model using a plurality of preset side surge images to obtain a side surge detection model; Step S16: obtaining a surge side view image detection frame of the surge impact in each side view image through the side surge detection model, and defining a surge side view image detection frame as a vertical impact range.

6. The method for analyzing the stability of a deposit according to claim 1, wherein: Step S3, obtaining an axis-aligned bounding box consisting of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the accumulation body, including: Step S31: scaling the horizontal influence range and the vertical influence range corresponding to the maximum area to the same scale, and defining them as the horizontal maximum influence range and the vertical maximum influence range, respectively; Step S32: Mapping the horizontal maximum influence range and the vertical maximum influence range to the preset area through a homography matrix to obtain the coordinates of four corners of the horizontal maximum influence range and the coordinates of four corners of the vertical maximum influence range respectively; Step S33: Obtain an axis-aligned bounding box of eight corner coordinates, where the axis-aligned bounding box is the three-dimensional arrangement range.

7. The method for analyzing the stability of a deposit according to claim 1, wherein: The equilibrium equation in step S8 is represented by equation (1): （1）； in, is the safety factor, is the effective cohesion of the stack, is the sliding surface length of the deposit, is the bottom normal force of the pile, is the pore water pressure of the deposit, is the effective internal friction angle of the pile, is the deadweight of the pile, is the angle between the equivalent static force and the sliding surface of the stack, is the equivalent static force.

8. A system for analyzing the stability of a pile under surge impact conditions, wherein the system is applied to the method for analyzing the stability of a pile according to any one of claims 1 to 7, and is characterized in that: The stack stability analysis system comprises: A surge impact range acquisition module is used to acquire the horizontal impact range and vertical impact range of the surge impact through computer vision based on a number of shooting time intervals; A surge impact range prediction module is used to predict the future horizontal impact range and vertical impact range of the landslide surge impact through all horizontal impact ranges and all vertical impact ranges based on a machine learning machine; A three-dimensional arrangement range definition module is used to obtain an axis-aligned bounding box composed of the maximum area of ​​all horizontal influence ranges and all vertical influence ranges as the three-dimensional arrangement range of the impact load collection points of the accumulation body; An impact load collection point arrangement module is configured to evenly arrange a plurality of impact load collection points at a preset array density in the above-water portion, the water surface, and the underwater portion of the three-dimensional arrangement range, with the impact load collection points being located at the edges of the three-dimensional arrangement range; An impact load data acquisition module, configured to acquire impact load data of the accumulation body through all impact load acquisition points based on a plurality of acquisition time intervals, wherein the impact load data includes impact load force and impact load action duration; An impact load velocity conversion module, configured to convert all impact load data into impact load velocity by using the momentum theorem based on the mass of the accumulation body; An equivalent static force conversion module is used to obtain an impact acceleration based on the impact load velocity of the adjacent impact load action duration, and convert the current impact acceleration into an equivalent static force through the mass of the accumulation body; Safety factor calculation module, used to substitute each equivalent static force into the equilibrium equation of the limit equilibrium method and obtain several safety factors along the time series; The instability risk data definition module is used to define all safety factors below a critical value and corresponding time stamps as instability risk data of the accumulation body.

9. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the method for analyzing the stability of a pile as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the method for analyzing the stability of a deposit as claimed in any one of claims 1 to 7 can be implemented.

Images