A method and system for monitoring excavation and filling in a reservoir area of ​​a pumped storage power station

Abstract

The present application discloses a method and system for monitoring excavation and filling in a reservoir area of ​​a pumped storage power station, which relates to the technical field of geological disaster prevention and control. The method analyzes the deformation characteristics of the excavation and filling area through remote sensing interpretation and time series technology, and simultaneously performs time series prediction on the analyzed deformation characteristics, thereby realizing the determination and prediction of the potential collapse characteristics of the excavation and filling area. Finally, the possible sliding surface of the excavation and filling area is confirmed through the predicted future deformation characteristics, so that the excavation and filling construction has quantitative graphic data support and the subsequent prevention and control is forward-looking. Certain prevention and control measures can be adopted before the excavation and filling area is actually deformed and damaged, thereby ensuring the safety of the excavation and filling construction.

Description

Technical Field

[0001] The present application relates to the technical field of geological disaster prevention and control, and in particular to a method and system for monitoring excavation and filling in a reservoir area of ​​a pumped-storage power station. Background Art

[0002] Pumped-storage power stations are hydropower stations that can use electricity during low load periods to pump water to the upper reservoir, and then release water to the lower reservoir for power generation during peak load periods. They are also called storage hydropower stations. Pumped-storage power stations can convert excess electricity during low load periods into high-value electricity during peak load periods. They are also suitable for frequency and phase modulation, stabilizing the frequency and voltage of the power system, and are suitable for emergency standby. They can also improve the efficiency of thermal power plants and nuclear power plants in the system. As a mature energy storage technology, pumped-storage power stations can play a variety of functions in the power system, such as peak-to-valley shifting, energy storage, frequency modulation, phase modulation, emergency standby, and black start.

[0003] Cut and fill construction generally has the characteristics of complex geological conditions, diverse earth and stone materials, huge engineering volume, and the resulting problems of site stability, fill settlement and differential settlement, slope instability, etc.

[0004] At present, physical monitoring or stress monitoring is usually used for excavation and filling monitoring of reservoir area excavation and filling construction. The vibration data obtained by the physical monitoring vibration sensor is used to determine whether the excavation and filling is safe, or the stress meter and displacement meter are used to determine whether the excavation and filling is safe. Since the above monitoring methods all require different monitoring equipment to be deployed on-site to achieve monitoring, but the amount of earth and stone in the excavation and filling is constantly changing, the above monitoring means need to constantly update the installation position of the equipment, resulting in more manpower and material resources used for safety monitoring, and each deployment of monitoring equipment requires a certain amount of time and cost, which is time-consuming and labor-intensive.‌ Summary of the invention

[0005] The main purpose of the present application is to provide a method and system for monitoring excavation and filling in the reservoir area of ​​a pumped storage power station, so as to solve the problem of low accuracy of excavation and filling monitoring for slope instability in the prior art.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] A method for monitoring excavation and filling in a pumped-storage power station reservoir area, wherein the pumped-storage power station reservoir area is applied to a pumped-storage power station under construction in a preset area, wherein the pumped-storage power station under construction includes a preset excavation area and a filling area, and the excavation and filling monitoring method comprises:

[0008] Step S1, obtaining a plurality of excavation digital elevation surfaces of the excavation area and a plurality of filling digital elevation surfaces of the filling area respectively through remote sensing interpretation at preset time intervals;

[0009] Step S2, analyzing a plurality of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time series composed of all preset time periods;

[0010] Step S3, defining all deformation displacement vectors within a same preset time period as an excavation deformation displacement vector data set;

[0011] Step S4, learning and training all excavation deformation displacement vector data sets through a machine learning machine, and obtaining an excavation deformation displacement vector prediction data set based on a preset prediction step number;

[0012] Step S5, marking the future excavation deformation displacement vectors exceeding a preset displacement threshold in the excavation deformation displacement vector prediction data set as excavation geological deformation monitoring points;

[0013] Step S6, respectively obtaining the geographical coordinates of each excavation geological deformation monitoring point;

[0014] Step S7, obtaining the possible sliding surface of the excavation slope in the excavation area based on the geographical coordinates of all excavation geological deformation monitoring points;

[0015] Step S8, repeating steps S2 to S7 with all the fill digital elevation surfaces as the main body to obtain the possible sliding surface of the fill slope in the fill area;

[0016] Step S9, sending the possible sliding surface of the excavation and the possible sliding surface of the filling to an external visual monitoring terminal.

[0017] As a further improvement of the present application, step S2, parsing a plurality of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time sequence composed of all preset time periods, includes:

[0018] Step S21, receiving raw SAR data of the excavation area based on all preset time periods from a satellite observation terminal;

[0019] Step S22, removing atmospheric delay and orbit error from all original SAR data, and obtaining a precise SAR data based on the original SAR data;

[0020] Step S23, performing differentiation on all precise SAR data of the same preset time period to obtain an interference image;

[0021] Step S24, sorting all interference images based on the linear time sequence;

[0022] Step S25, sequentially differentiating the interference images of adjacent preset time periods, and obtaining a differential interference pattern for every two interference images;

[0023] Step S26, unwrapping the phase information of each differential interferogram to obtain all surface deformation phase data of the excavation area;

[0024] Step S27, converting all surface deformation phase data into map coordinates, and fusing the data with the digital elevation model of the excavation area to obtain surface deformation coordinate data;

[0025] Step S28, analyzing all surface deformation coordinate data through SBAS-InSAR to obtain all excavation deformation displacement vectors.

[0026] As a further improvement of the present application, step S4, learning and training all vector data sets through a machine learning machine, and obtaining a prediction data set of excavation deformation displacement vectors based on a preset prediction step number, including:

[0027] Step S41, performing vector normalization processing on all vector data sets to obtain a normalized data set based on a preset time period;

[0028] Step S42, dividing the current normalized data set into a training set and a validation set according to a preset ratio;

[0029] Step S43, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected;

[0030] Step S44, inputting the training set into the input layer, performing several trainings through the neural network model, and obtaining a root mean square error between the validation set and the current training result based on each training;

[0031] Step S45, obtaining the minimum value of all root mean square errors;

[0032] Step S46, obtaining a training result corresponding to the minimum value as a prediction model for excavation deformation displacement vector;

[0033] Step S47: predicting an excavation deformation displacement vector prediction data set based on a preset prediction step number by using the excavation deformation displacement vector prediction model.

[0034] As a further improvement of the present application, step S7, based on the geographic coordinates of all excavation geological deformation monitoring points, obtains the possible sliding surface of the excavation slope in the excavation area, including:

[0035] Step S71, inputting all excavation geological deformation monitoring points into the excavation digital elevation surface of the monitoring section;

[0036] Step S72, drawing projection vector lines of each geographic coordinate based on the same vertical plane on the cut digital elevation surface;

[0037] Step S73, respectively obtaining the perpendicular line of each projection vector line and obtaining all the intersection points between all the perpendicular lines;

[0038] Step S74, deleting outlier points from all intersection points, and defining the remaining intersection points as valid intersection points;

[0039] Step S75, obtaining the minimum covering circle of all valid intersection points;

[0040] Step S76, sliding the respective perpendicular lines on each projection vector line respectively so that the minimum coverage circle reaches the minimum radius;

[0041] Step S77, obtaining the center of the minimum covering circle that reaches the minimum radius and using it as the center of the possible sliding surface of the excavation slope;

[0042] Step S78, defining the distance between the center of the possible sliding surface of the excavated slope and the front edge of the excavated area as the radius of the deformation failure surface, and obtaining the possible sliding surface of the excavated slope.

[0043] As a further improvement of the present application, in step S74, outlier points in all intersection points are deleted, and the remaining intersection points are defined as valid intersection points, including:

[0044] Step S741, define the intersection data set of all intersection points ,in is the number of all intersection points;

[0045] Step S742: Divide horizontally and vertically, and obtain the intersection point abscissa data set based on horizontal division , based on the vertical division, the vertical coordinate data set of the intersection is obtained ;

[0046] Step S743, calculate the intersection point horizontal coordinate data set Expectations , Standard Deviation , and the intersection ordinate dataset Expectations , Standard Deviation ;

[0047] Step S744, when and When is a valid intersection point;

[0048] Step S745, when or When is an outlier;

[0049] Step S746: Delete the intersection points determined to be outliers, and define the remaining intersection points as the valid intersection points.

[0050] As a further improvement of the present application, step S75, obtaining the minimum covering circle of all valid intersection points, includes:

[0051] Step S751, generating a rectangular coordinate system based on the same vertical plane;

[0052] Step S752, converting all valid intersection points into coordinate points according to the rectangular coordinate system;

[0053] Step S753, obtain any two coordinate points from all coordinate points and , and the line segment Get the initial circle as the diameter , where the subscript 2 represents the number of coordinate points within the initial circle;

[0054] Step S754, traverse each coordinate point in turn and determine the Coordinate points Is it located in the first iteration circle? , Coordinate points Not located in the first iteration circle If yes, execute step S755;

[0055] Step S755, using line segment The diameter of the second iteration circle is obtained ;

[0056] Step S756, determine Coordinate points Is it located in the second iteration circle? In which , Coordinate points There is no circle located in the second iteration If yes, execute step S757;

[0057] Step S757, using line segment The third iteration circle is obtained as the diameter ;

[0058] Step S758, determine Coordinate points Is it located in the third iteration circle? In which , Coordinate points Not located in the third iteration circle If yes, execute step S759;

[0059] Step S759, connect , , A triangle is formed, and a circumscribed circle of the triangle is obtained, where the circumscribed circle is the minimum covering circle.

[0060] As a further improvement of the present application, step S8, repeating steps S2 to S7 with all fill digital elevation surfaces as the main body, to obtain the possible sliding surface of the fill slope in the fill area, including:

[0061] Step S81, analyzing a plurality of fill deformation displacement vectors of the fill digital elevation surface through a linear time series composed of all preset time periods;

[0062] Step S82, defining all deformation displacement vectors within a same preset time period as a fill deformation displacement vector data set;

[0063] Step S83, learning and training all the fill deformation displacement vector data sets through a machine learning machine, and obtaining a fill deformation displacement vector prediction data set based on a preset prediction step number;

[0064] Step S84, marking the future fill deformation displacement vectors exceeding the preset displacement threshold in the fill deformation displacement vector prediction data set as fill geological deformation monitoring points;

[0065] Step S85, respectively obtaining the geographical coordinates of each fill geological deformation monitoring point;

[0066] Step S86, obtaining the possible sliding surface of the fill slope in the fill area based on the geographic coordinates of all fill geological deformation monitoring points.

[0067] To achieve the above objectives, this application also provides the following technical solutions:

[0068] A cutting and filling monitoring system for a reservoir area of ​​a pumped storage power station, the cutting and filling monitoring system is applied to the cutting and filling monitoring method as described above, and the cutting and filling monitoring system comprises:

[0069] A cut-fill digital elevation surface acquisition module is used to respectively acquire a plurality of cut digital elevation surfaces of the cut area and a plurality of fill digital elevation surfaces of the fill area through remote sensing interpretation at preset time intervals;

[0070] A cut deformation displacement vector acquisition module is used to analyze a plurality of cut deformation displacement vectors of the cut digital elevation surface through a linear time sequence composed of all preset time periods;

[0071] The excavation deformation displacement vector data set definition module is used to define all deformation displacement vectors within the same preset time period as an excavation deformation displacement vector data set;

[0072] The excavation deformation displacement vector prediction data set acquisition module is used to learn and train all excavation deformation displacement vector data sets through a machine learning machine, and obtain an excavation deformation displacement vector prediction data set based on a preset prediction step number;

[0073] An excavation geological deformation monitoring point marking module is used to mark the future excavation deformation displacement vector exceeding a preset displacement threshold in the excavation deformation displacement vector prediction data set as an excavation geological deformation monitoring point;

[0074] A module for acquiring geographic coordinates of excavation geological deformation monitoring points, used to respectively acquire the geographic coordinates of each excavation geological deformation monitoring point;

[0075] A possible sliding surface acquisition module for the excavation slope, used to acquire the possible sliding surface of the excavation slope in the excavation area based on the geographical coordinates of all excavation geological deformation monitoring points;

[0076] A fill slope possible sliding surface acquisition module is used to repeatedly execute the excavation deformation displacement vector acquisition module to the excavation slope possible sliding surface acquisition module based on all fill digital elevation surfaces to obtain the fill slope possible sliding surface of the fill area;

[0077] The possible sliding surface sending module of the excavation and filling is used to send the possible sliding surface of the excavation and the possible sliding surface of the filling to an external visual monitoring terminal.

[0078] To achieve the above objectives, this application also provides the following technical solutions:

[0079] An electronic device 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 excavation and filling monitoring method as described above is implemented.

[0080] To achieve the above objectives, this application also provides the following technical solutions:

[0081] A storage medium stores program instructions, and when the program instructions are executed by a processor, the above-mentioned excavation and filling monitoring method can be implemented.

[0082] The present application obtains several excavation digital elevation surfaces of the excavation area and several fill digital elevation surfaces of the fill area respectively through remote sensing interpretation at intervals of preset time periods; analyzes several excavation deformation displacement vectors of the excavation digital elevation surface through a linear time series composed of all preset time periods; defines all deformation displacement vectors within the same preset time period as an excavation deformation displacement vector data set; learns and trains all excavation deformation displacement vector data sets through a machine learning machine, and obtains an excavation deformation displacement vector prediction data set based on a preset prediction step number; marks future excavation deformation displacement vectors in the excavation deformation displacement vector prediction data set that exceed a preset displacement threshold as excavation geological deformation monitoring points; obtains the geographic coordinates of each excavation geological deformation monitoring point respectively; obtains the possible sliding surface of the excavation slope in the excavation area based on the geographic coordinates of all excavation geological deformation monitoring points; repeats the above steps with all fill digital elevation surfaces as the main body to obtain the possible sliding surface of the fill slope in the fill area; and sends the possible sliding surface of the excavation and the possible sliding surface of the fill to an external visual monitoring terminal. This application uses remote sensing interpretation and time series technology to analyze the deformation characteristics of the cut and fill area, and at the same time performs time series prediction on the analyzed deformation characteristics, thereby realizing the determination and prediction of the potential collapse characteristics of the cut and fill. Finally, the possible sliding surface of the cut and fill is confirmed through the predicted future deformation characteristics, so that the cut and fill construction has quantitative graphic data support and the subsequent prevention and control is forward-looking. Certain prevention and control measures can be adopted before the cut and fill actually deforms and damages, thereby ensuring the safety of the cut and fill construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A schematic diagram of the steps of an embodiment of a method for monitoring the excavation and filling of a reservoir area of ​​a pumped storage power station of the present application;

[0084] Figure 2 This is a functional module diagram of an embodiment of a digging and filling monitoring system for a pumped storage power station reservoir area of ​​the present application;

[0085] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0086] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0087] The following application will combine the drawings in the embodiments to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and 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 position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0089] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0090] like Figure 1 As shown, this embodiment provides an embodiment of a method for monitoring excavation and filling in a pumped-storage power station reservoir area. In this embodiment, the pumped-storage power station reservoir area is applied to a pumped-storage power station under construction in a preset area, and the pumped-storage power station under construction includes a pre-set excavation area and a filling area.

[0091] Preferably, both the excavation area and the filling area may include the nearest slopes around each other to ensure the comprehensiveness of monitoring.

[0092] Specifically, the excavation and filling monitoring method includes the following steps:

[0093] Step S1, obtaining a plurality of digital elevation surfaces of the excavation area and a plurality of digital elevation surfaces of the filling area through remote sensing interpretation at preset time intervals.

[0094] Preferably, both the excavation surface and the fill surface are unique modeling methods of Civil 3D. These two surfaces can be directly selected in the option bar of Civil 3D. The specific establishment details are handled by Civil 3D itself and will not be repeated in this embodiment.

[0095] It is worth noting that in actual operation, there is a problem of selecting the upper and lower directions of the surfaces in the fill volume and the cut volume. The upper and lower directions of the surfaces in the fill volume and the cut volume. The fill volume is the area enclosed by the upper part of the original surface and the lower part of the design surface (a wrong understanding is that the fill volume is the design surface at the top and the original surface at the bottom, so when selecting the conditions, the upper and lower directions are also selected). The cut volume is the area enclosed by the lower part of the original surface and the upper part of the design surface.

[0096] Step S2, analyzing a plurality of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time series composed of all preset time periods.

[0097] Preferably, SBAS-InSAR technology can be used to complete step S2. Preferably, differential interferometry short baseline set temporal deformation and damage analysis technology (Small Baseline Subset InSAR, SBAS-InSAR) is an InSAR time series method based on multiple main images. It combines a large amount of SAR data into an interference subset with multiple main images through the short baseline principle. The interference baseline length in each subset is lower than the critical baseline value, the time baseline is as short as possible, and the SAR image baseline distance between the sets is large. In this way, the temporal and spatial decorrelation is overcome, so SBAS-InSAR can obtain more reliable monitoring results with less data. Based on the short baseline set principle, SBAS-InSAR has multiple main images, but one of the images still needs to be selected as the common main image for registration; after forming each interference subset, the external reference Digital Elevation Model (DEM) data is used to simulate and remove the terrain phase relative to each interference, and then a time series differential interference atlas is generated; after phase unwrapping, the phase information of each coherent target is obtained, including deformation phase, atmospheric delay phase, orbit error phase and other information. Each error phase can be removed in the time series by filtering method or polynomial model; since SBAS-InSAR has multiple main images, each interference subset is prone to equation rank deficiency when jointly solving, so the singular value decomposition method is introduced, and the least squares principle is used to obtain the surface time series deformation information.

[0098] Step S3: defining all deformation displacement vectors within a same preset time period as an excavation deformation displacement vector data set.

[0099] Preferably, the surface deformation information obtained by SBAS-InSAR analysis can be formed into a vector based on adjacent time series, the length of the vector is the surface deformation amplitude of the adjacent time series, and the direction of the vector is the surface deformation direction of the adjacent time series.

[0100] Step S4, learning and training all excavation deformation displacement vector data sets through a machine learning machine, and obtaining an excavation deformation displacement vector prediction data set based on a preset prediction step number.

[0101] Preferably, this embodiment may adopt a neural network.

[0102] Step S5: Mark the future excavation deformation displacement vectors exceeding a preset displacement threshold in the excavation deformation displacement vector prediction data set as excavation geological deformation monitoring points.

[0103] Preferably, the preset displacement threshold may be set to 0.5 m.

[0104] Step S6, respectively obtaining the geographical coordinates of each excavation geological deformation monitoring point.

[0105] Step S7, obtaining the possible sliding surface of the excavation slope in the excavation area based on the geographic coordinates of all excavation geological deformation monitoring points.

[0106] Step S8, repeating steps S2 to S7 based on all the fill digital elevation surfaces to obtain the possible sliding surface of the fill slope in the fill area.

[0107] Step S9, sending the possible sliding surface of the excavation and the possible sliding surface of the filling to an external visual monitoring terminal.

[0108] Furthermore, in step S2, a plurality of excavation deformation displacement vectors of the excavation digital elevation surface are analyzed through a linear time series composed of all preset time periods, including:

[0109] Step S21, receiving raw SAR data of the excavation area based on all preset time periods from the satellite observation terminal.

[0110] Step S22, removing atmospheric delay and orbit error from all original SAR data, and obtaining a precise SAR data based on the original SAR data.

[0111] Step S23: Differentiate all precise SAR data in the same preset time period to obtain an interference image.

[0112] Step S24, sorting all interference images based on a linear time sequence.

[0113] Step S25, sequentially differentiating the interference images of adjacent preset time periods, and obtaining a differential interference pattern for every two interference images.

[0114] Step S26, unwrapping the phase information of each differential interferogram to obtain all surface deformation phase data of the excavation area.

[0115] Step S27, converting all the surface deformation phase data into map coordinates, and fusing the data with the digital elevation model of the excavation area to obtain surface deformation coordinate data.

[0116] Step S28, analyzing all surface deformation coordinate data through SBAS-InSAR to obtain all excavation deformation displacement vectors.

[0117] Preferably, steps S21 to S28 can be automatically completed in SARscape, and the user only needs to select a small number of parameters and settings of SARscape. The tutorial for using SARscape can be directly obtained from public channels.

[0118] Specifically, the processing flow of SBAS-InSAR is as follows:

[0119] ①Data collection and preset: SAR data collection; DEM data download and placement; precise orbit data download and placement; making study area range vector; SARscape Preferences preset.

[0120] ②SAR data preprocessing: import data; optional files setting; parameter setting.

[0121] ③Generate connection graph: input data; set optional files; set parameters; view output files and connection graph.

[0122] ④Interferometric Process: Select the engineering file auxiliary.sml obtained in the previous step in Input Files; make a reference DEM; set parameters; output file; set optional files (Avoid Moving Area File, Optional Water Vapour File List, Classification Mask File).

[0123] ⑤SBAS Edit Connection Graph: Open the auxiliary.sml file, the software automatically loads the connection graph and automatically selects the main image; parameter description for connection graph editing; connection graph editing operations; track refinement and re-leveling.

[0124] It is worth noting that SBAS-InSAR processing software includes SARscape, IPTA, StaMPS and MintPya, etc. In this embodiment, SARscape is preferably used in the above processing flow.

[0125] Further, in step S4, all vector data sets are learned and trained by a machine learning machine, and a prediction data set of excavation deformation displacement vectors is obtained based on a preset prediction step number, including:

[0126] Step S41, performing vector normalization processing on all vector data sets to obtain a normalized data set based on a preset time period.

[0127] Preferably, vector normalization is a method of scaling a vector to a unit vector. The main purpose is to only consider the direction of the vector without affecting its magnitude. The mathematical principle of vector normalization is to divide the vector by its modulus to obtain a unit vector.

[0128] Step S42, dividing the current normalized data set into a training set and a validation set according to a preset ratio.

[0129] Preferably, the preset ratio can be set to 8:2, so as to divide the normalized data set into a training set and a sample set in a ratio of 8:2.

[0130] Step S43, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially signal-connected.

[0131] The neural network model is represented by the following formula:

[0132] .

[0133] in, is a neural network model; The input layer input nodes, each of which corresponds to a normalized data set in the training set. The input layer The first input node to the hidden layer The weights of the input nodes; is connected to the hidden layer The bias of the input node; is the bias of the output layer; is the activation function; the number in the brackets of the symbol subscript is the number of layers, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer.

[0134] It should be noted that the meanings of the symbols in the above principle description are not interchangeable with the meanings of other symbols in the context.

[0135] Step S44, input the training set to the input layer, perform several trainings through the neural network model, and obtain the root mean square error between the verification set and the current training result based on each training.

[0136] Step S45, obtaining the minimum value of all root mean square errors.

[0137] Step S46, obtaining the training result corresponding to the minimum value as the excavation deformation displacement vector prediction model.

[0138] Step S47: predicting an excavation deformation displacement vector prediction data set based on a preset prediction step number by using the excavation deformation displacement vector prediction model.

[0139] Preferably, the training model training a neural network usually requires providing a large amount of data, namely a data set; the data set is generally divided into three categories, namely the above-mentioned training set (training set), validation set (validation set) and test set (test set).

[0140] Among them, one epoch is the process of training once with all the samples in the training set. The so-called training once refers to one forward pass and one back pass. When the number of samples in an epoch (i.e., training set) is too large, training once may consume too much time, and it is not necessary to use all the data in the training set for each training. In this case, the entire training set needs to be divided into multiple small blocks, that is, divided into multiple batches for training. An epoch consists of one or more batches, where a batch is a part of the training set. Each training process only uses a part of the data, i.e., a batch. The process of training a batch is an iteration.

[0141] Preferably, the neural network training specifically includes a perceptron, which is composed of two layers of neurons. The input layer receives external input signals and transmits them to the output layer. The output layer is MP neurons, and the step function is .

[0142] Preferably, given a training data set, the weights ( =1,2,...,n) and training bias It can be obtained through learning, It can be understood as the weight corresponding to a fixed value of -1,0. .

[0143] It should be noted that the step function here has no interchangeable symbolic meaning with other formulas in the embodiment. This step function is only used for principle explanation and does not participate in the calculation of other formulas.

[0144] Preferably, in this embodiment, the number of neural network training times can be set to 10,000 times.

[0145] Preferably, the learning rate from the 1st to the 5000th epoch can be set to 0.01, the learning rate from the 5001st to the 7500th epoch can be set to 0.001, and the learning rate from the 7501st to the 10000th epoch can be set to 0.0001.

[0146] It can be understood that the neural network training of this embodiment mainly includes the following ideas:

[0147] ① Initialize the weights and bias items in the network.

[0148] Initializing parameter values ​​(output unit weights, bias terms and hidden unit weights, bias terms are all model parameters) is to activate forward propagation, obtain the output value of each layer element, and then obtain the value of the loss function.

[0149] ②Activate forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0150] ③According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0151] Calculate various errors, calculate the gradient of the parameters with respect to the loss function, or calculate partial derivatives according to the chain rule of calculus. For partial derivatives of vectors or matrices in a composite function, the partial derivative of the function inside the composite function is always multiplied on the left; for partial derivatives of scalars in a composite function, the partial derivative of the function inside the composite function can be multiplied on the left or on the right.

[0152] ④Update the weights and bias items in the neural network.

[0153] ⑤ Repeat ②~④ until the loss function is less than the preset bias or the number of iterations is used up, and the parameters output at this time are the current optimal parameters.

[0154] Further, step S7, based on the geographic coordinates of all excavation geological deformation monitoring points, the possible sliding surface of the excavation slope in the excavation area is obtained, including:

[0155] Step S71, inputting all excavation geological deformation monitoring points into the excavation digital elevation surface of the monitoring section.

[0156] Step S72: Draw the projection vector line of each geographic coordinate based on the same vertical plane on the cut digital elevation surface.

[0157] Step S73, respectively obtain the perpendicular line of each projection vector line and obtain all the intersection points between all the perpendicular lines.

[0158] Step S74, deleting outlier points from all intersection points, and defining the remaining intersection points as valid intersection points.

[0159] Step S75, obtaining the minimum covering circle of all valid intersection points.

[0160] Step S76, sliding the respective perpendicular lines on each projection vector line respectively so that the minimum coverage circle reaches the minimum radius.

[0161] Step S77, obtaining the center of the minimum covering circle that reaches the minimum radius and using it as the center of the possible sliding surface of the excavation slope.

[0162] Step S78, defining the distance between the center of the possible sliding surface of the excavated slope and the front edge of the excavated area as the radius of the deformation failure surface, and obtaining the possible sliding surface of the excavated slope.

[0163] Furthermore, in step S74, outlier points in all intersection points are deleted, and the remaining intersection points are defined as valid intersection points, including:

[0164] Step S741, define the intersection data set of all intersection points ,in is the number of all intersection points.

[0165] Step S742: Divide horizontally and vertically, and obtain the intersection point abscissa data set based on horizontal division , based on the vertical division, the vertical coordinate data set of the intersection is obtained .

[0166] Step S743, calculate the intersection point horizontal coordinate data set Expectations , Standard Deviation , and the intersection ordinate dataset Expectations , Standard Deviation .

[0167] Step S744, when and When is a valid intersection point.

[0168] Step S745, when or When For outliers.

[0169] Step S746: Delete the intersection points determined to be outliers, and define the remaining intersection points as valid intersection points.

[0170] Furthermore, step S75, obtaining the minimum covering circle of all valid intersection points includes:

[0171] Step S751, generating a rectangular coordinate system based on the same vertical plane.

[0172] Step S752: convert all valid intersection points into coordinate points according to a rectangular coordinate system.

[0173] Step S753, obtain any two coordinate points from all coordinate points and , and the line segment Get the initial circle as the diameter , where the subscript 2 represents the number of coordinate points in the initial circle.

[0174] Step S754, traverse each coordinate point in turn and determine the Coordinate points Is it located in the first iteration circle? , Coordinate points Not located in the first iteration circle If the value is within 100, execute step S755.

[0175] Step S755, using line segment The diameter of the second iteration circle is obtained .

[0176] Step S756, determine Coordinate points Is it located in the second iteration circle? In which , Coordinate points Not located in the second iteration circle If the value is within 100, execute step S757.

[0177] Step S757, using line segment The third iteration circle is obtained as the diameter .

[0178] Step S758, determine Coordinate points Is it located in the third iteration circle? In which , Coordinate points Not located in the third iteration circle If the value is within 100, execute step S759.

[0179] Step S759, connect , , A triangle is formed and the circumscribed circle of the triangle is obtained. The circumscribed circle is the minimum covering circle.

[0180] Further, step S8, taking all the fill digital elevation surfaces as the main body, repeating steps S2 to S7, to obtain the possible sliding surface of the fill slope in the fill area, including:

[0181] Step S81, analyzing a plurality of fill deformation displacement vectors of the fill digital elevation surface through a linear time series composed of all preset time periods.

[0182] Step S82: defining all deformation displacement vectors within a same preset time period as a fill deformation displacement vector data set.

[0183] Step S83, learning and training all the fill deformation displacement vector data sets through a machine learning machine, and obtaining a fill deformation displacement vector prediction data set based on a preset prediction step number.

[0184] Step S84, marking the future fill deformation displacement vectors exceeding the preset displacement threshold in the fill deformation displacement vector prediction data set as fill geological deformation monitoring points.

[0185] Step S85, respectively obtaining the geographical coordinates of each fill geological deformation monitoring point.

[0186] Step S86, obtaining the possible sliding surface of the fill slope in the fill area based on the geographic coordinates of all fill geological deformation monitoring points.

[0187] It should be noted that it is also necessary to repeat all sub-steps from step S2 to step S7 based on all fill digital elevation surfaces. Due to the same principle and similar content, this embodiment will not repeat the process of obtaining the fill digital elevation surface.

[0188] In this embodiment, a plurality of excavation digital elevation surfaces and a plurality of fill digital elevation surfaces are respectively obtained in the excavation area and in the fill area through remote sensing interpretation at intervals of preset time periods; a plurality of excavation deformation displacement vectors of the excavation digital elevation surfaces are parsed through a linear time series composed of all preset time periods; all deformation displacement vectors within the same preset time period are defined as an excavation deformation displacement vector data set; all excavation deformation displacement vector data sets are learned and trained by a machine learning machine, and an excavation deformation displacement vector prediction data set is obtained based on a preset prediction step number; future excavation deformation displacement vectors in the excavation deformation displacement vector prediction data set that exceed a preset displacement threshold are marked as excavation geological deformation monitoring points; the geographic coordinates of each excavation geological deformation monitoring point are respectively obtained; the possible sliding surface of the excavation slope in the excavation area is obtained based on the geographic coordinates of all excavation geological deformation monitoring points; the above steps are repeated with all fill digital elevation surfaces as the main body to obtain the possible sliding surface of the fill slope in the fill area; and the possible sliding surface of the excavation and the possible sliding surface of the fill are sent to an external visual monitoring terminal. This embodiment analyzes the deformation characteristics of the cut and fill area through remote sensing interpretation and time series technology, and performs time series prediction on the analyzed deformation characteristics, thereby realizing the determination and prediction of potential collapse characteristics of the cut and fill. Finally, the possible sliding surface of the cut and fill is confirmed through the predicted future deformation characteristics, so that the cut and fill construction has quantitative graphic data support and the subsequent prevention and control is forward-looking. Certain prevention and control measures can be adopted before the cut and fill actually undergoes deformation and damage, thereby ensuring the safety of the cut and fill construction.

[0189] like Figure 2 As shown, this embodiment provides an embodiment of a cutting and filling monitoring system for a reservoir area of ​​a pumped storage power station. In this embodiment, the cutting and filling monitoring system is applied to the cutting and filling monitoring method as in the above-mentioned embodiment.

[0190] Specifically, the excavation and filling monitoring system includes an excavation and filling digital elevation surface acquisition module 1, an excavation deformation displacement vector acquisition module 2, an excavation deformation displacement vector data set definition module 3, an excavation deformation displacement vector prediction data set acquisition module 4, an excavation geological deformation monitoring point marking module 5, an excavation geological deformation monitoring point geographic coordinate acquisition module 6, an excavation slope possible sliding surface acquisition module 7, a fill slope possible sliding surface acquisition module 8, and an excavation and filling possible sliding surface sending module 9, which are electrically connected in sequence. The fill slope possible sliding surface acquisition module 8 is also electrically connected to the excavation deformation displacement vector acquisition module 2.

[0191] Among them, the excavation and filling digital elevation surface acquisition module 1 is used to obtain a number of excavation digital elevation surfaces in the excavation area and a number of fill digital elevation surfaces in the fill area through remote sensing interpretation at preset time intervals; the excavation deformation displacement vector acquisition module 2 is used to parse a number of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time series composed of all preset time periods; the excavation deformation displacement vector data set definition module 3 is used to define all deformation displacement vectors within the same preset time period as an excavation deformation displacement vector data set; the excavation deformation displacement vector prediction data set acquisition module 4 is used to learn and train all excavation deformation displacement vector data sets through a machine learning machine, and obtain an excavation deformation displacement vector prediction data set based on a preset prediction step number; the excavation geological deformation monitoring point The marking module 5 is used to mark the future excavation deformation displacement vectors exceeding the preset displacement threshold in the excavation deformation displacement vector prediction data set as excavation geological deformation monitoring points; the excavation geological deformation monitoring point geographic coordinate acquisition module 6 is used to respectively obtain the geographic coordinates of each excavation geological deformation monitoring point; the excavation slope possible sliding surface acquisition module 7 is used to obtain the excavation slope possible sliding surface in the excavation area based on the geographic coordinates of all excavation geological deformation monitoring points; the fill slope possible sliding surface acquisition module 8 is used to repeatedly execute the excavation deformation displacement vector acquisition module to the excavation slope possible sliding surface acquisition module with all fill digital elevation surfaces as the main body to obtain the fill slope possible sliding surface in the fill area; the excavation and fill possible sliding surface sending module 9 is used to send the excavation possible sliding surface and the fill possible sliding surface to the external visual monitoring terminal.

[0192] Furthermore, the excavation deformation displacement vector acquisition module 2 specifically includes a first excavation deformation displacement vector acquisition submodule, a second excavation deformation displacement vector acquisition submodule, a third excavation deformation displacement vector acquisition submodule, a fourth excavation deformation displacement vector acquisition submodule, a fifth excavation deformation displacement vector acquisition submodule, a sixth excavation deformation displacement vector acquisition submodule, a seventh excavation deformation displacement vector acquisition submodule, and an eighth excavation deformation displacement vector acquisition submodule, which are electrically connected in sequence; the first excavation deformation displacement vector acquisition submodule is electrically connected to the cut and fill digital elevation surface acquisition module 1, and the eighth excavation deformation displacement vector acquisition submodule is electrically connected to the excavation deformation displacement vector data set definition module 3 and the fill slope possible sliding surface acquisition module 8.

[0193] Among them, the first excavation deformation displacement vector acquisition submodule is used to receive the original SAR data of the excavation area based on all preset time periods from the satellite observation end; the second excavation deformation displacement vector acquisition submodule is used to remove the atmospheric delay and orbit error of all the original SAR data, and obtain an accurate SAR data based on an original SAR data; the third excavation deformation displacement vector acquisition submodule is used to differentiate all the accurate SAR data of the same preset time period to obtain an interference image; the fourth excavation deformation displacement vector acquisition submodule is used to sort all the interference images based on a linear time series; the fifth excavation deformation displacement vector acquisition submodule is used to obtain the interference image based on the linear time series. The acquisition submodule is used to sequentially differentiate the interference images of adjacent preset time periods, and obtain a differential interference image for every two interference images; the sixth excavation deformation displacement vector acquisition submodule is used to untangle the phase information of each differential interference image to obtain all surface deformation phase data of the excavation area; the seventh excavation deformation displacement vector acquisition submodule is used to convert all surface deformation phase data into map coordinates, and perform data fusion with the digital elevation model of the excavation area to obtain surface deformation coordinate data; the eighth excavation deformation displacement vector acquisition submodule is used to parse all surface deformation coordinate data through SBAS-InSAR to obtain all excavation deformation displacement vectors.

[0194] Furthermore, the excavation deformation displacement vector prediction data set acquisition module 4 specifically includes a first excavation deformation displacement vector prediction data set acquisition submodule, a second excavation deformation displacement vector prediction data set acquisition submodule, a third excavation deformation displacement vector prediction data set acquisition submodule, a fourth excavation deformation displacement vector prediction data set acquisition submodule, a fifth excavation deformation displacement vector prediction data set acquisition submodule, a sixth excavation deformation displacement vector prediction data set acquisition submodule, and a seventh excavation deformation displacement vector prediction data set acquisition submodule, which are electrically connected in sequence; the first excavation deformation displacement vector prediction data set acquisition submodule is electrically connected to the excavation deformation displacement vector data set definition module 3, and the seventh excavation deformation displacement vector prediction data set acquisition submodule is electrically connected to the excavation geological deformation monitoring point marking module 5.

[0195] Among them, the first excavation deformation displacement vector prediction data set acquisition submodule is used to perform vector normalization processing on all vector data sets, and obtain a normalized data set based on a preset time period; the second excavation deformation displacement vector prediction data set acquisition submodule is used to divide the current normalized data set into a training set and a verification set according to a preset ratio; the third excavation deformation displacement vector prediction data set acquisition submodule is used to define a neural network model in which an input layer, a hidden layer, and an output layer are sequentially connected by signals; the fourth excavation deformation displacement vector prediction data set acquisition submodule is used to input the training set into the input layer, perform several trainings through the neural network model, and obtain the root mean square error between the verification set and the current training result based on each training; the fifth excavation deformation displacement vector prediction data set acquisition submodule is used to obtain the minimum value of all root mean square errors; the sixth excavation deformation displacement vector prediction data set acquisition submodule is used to obtain the training result corresponding to the minimum value as the excavation deformation displacement vector prediction model; the seventh excavation deformation displacement vector prediction data set acquisition submodule is used to predict an excavation deformation displacement vector prediction data set based on a preset prediction step number through the excavation deformation displacement vector prediction model.

[0196] Furthermore, the excavation slope possible sliding surface acquisition module 7 specifically includes a first excavation slope possible sliding surface acquisition submodule, a second excavation slope possible sliding surface acquisition submodule, a third excavation slope possible sliding surface acquisition submodule, a fourth excavation slope possible sliding surface acquisition submodule, a fifth excavation slope possible sliding surface acquisition submodule, a sixth excavation slope possible sliding surface acquisition submodule, a seventh excavation slope possible sliding surface acquisition submodule, and an eighth excavation slope possible sliding surface acquisition submodule, which are electrically connected in sequence; the first excavation slope possible sliding surface acquisition submodule is electrically connected to the excavation geological deformation monitoring point geographic coordinate acquisition module 6, and the eighth excavation slope possible sliding surface acquisition submodule is electrically connected to the fill slope possible sliding surface acquisition module 8.

[0197] Among them, the first excavation slope possible sliding surface acquisition submodule is used to input all excavation geological deformation monitoring points into the excavation digital elevation surface of the monitoring section; the second excavation slope possible sliding surface acquisition submodule is used to draw the projection vector line of each geographic coordinate based on the same vertical plane on the excavation digital elevation surface; the third excavation slope possible sliding surface acquisition submodule is used to obtain the perpendicular line of each projection vector line and obtain all the intersection points between all the perpendicular lines; the fourth excavation slope possible sliding surface acquisition submodule is used to delete the outliers among all the intersection points and define the retained intersection points as valid intersection points; The fifth excavation slope possible sliding surface acquisition submodule is used to obtain the minimum covering circle of all valid intersection points; the sixth excavation slope possible sliding surface acquisition submodule is used to slide the respective vertical lines on each projection vector line respectively so that the minimum covering circle reaches the minimum radius; the seventh excavation slope possible sliding surface acquisition submodule is used to obtain the center of the minimum covering circle that reaches the minimum radius and use it as the center of the excavation slope possible sliding surface; the eighth excavation slope possible sliding surface acquisition submodule is used to define the distance between the center of the excavation slope possible sliding surface and the front edge of the excavation area as the radius of the deformation failure surface, and obtain the excavation slope possible sliding surface.

[0198] Furthermore, the fourth excavation slope possible sliding surface acquisition submodule specifically includes a first excavation slope possible sliding surface acquisition unit, a second excavation slope possible sliding surface acquisition unit, a third excavation slope possible sliding surface acquisition unit, a fourth excavation slope possible sliding surface acquisition unit, a fifth excavation slope possible sliding surface acquisition unit, and a sixth excavation slope possible sliding surface acquisition unit, which are electrically connected in sequence; the first excavation slope possible sliding surface acquisition unit is electrically connected to the third excavation slope possible sliding surface acquisition submodule, and the sixth excavation slope possible sliding surface acquisition unit is electrically connected to the fifth excavation slope possible sliding surface acquisition submodule.

[0199] The first excavation slope possible sliding surface acquisition unit is used to define the intersection data set of all intersection points. ,in is the number of all intersection points; the second excavation slope possible sliding surface acquisition unit is used to obtain the intersection data set Divide horizontally and vertically, and obtain the intersection point abscissa data set based on horizontal division , based on the vertical division, the vertical coordinate data set of the intersection is obtained ; The third excavation slope possible sliding surface acquisition unit is used to calculate the intersection point horizontal coordinate data set Expectations , Standard Deviation , and the intersection ordinate dataset Expectations , Standard Deviation ; The fourth excavation slope possible sliding surface acquisition unit is used when and When is the effective intersection point; the fifth excavation slope possible sliding surface acquisition unit is used when or When The sixth excavation slope possible sliding surface acquisition unit is used to delete the intersection points judged as outliers and define the retained intersection points as valid intersection points.

[0200] Further, the fifth excavation slope possible sliding surface acquisition submodule specifically includes a seventh excavation slope possible sliding surface acquisition unit, an eighth excavation slope possible sliding surface acquisition unit, a ninth excavation slope possible sliding surface acquisition unit, a tenth excavation slope possible sliding surface acquisition unit, an eleventh excavation slope possible sliding surface acquisition unit, a twelfth excavation slope possible sliding surface acquisition unit, a thirteenth excavation slope possible sliding surface acquisition unit, a fourteenth excavation slope possible sliding surface acquisition unit, and a fifteenth excavation slope possible sliding surface acquisition unit, which are electrically connected in sequence; the seventh excavation slope possible sliding surface acquisition unit is electrically connected to the sixth excavation slope possible sliding surface acquisition unit, and the fifteenth excavation slope possible sliding surface acquisition unit is electrically connected to the sixth excavation slope possible sliding surface acquisition submodule.

[0201] Among them, the seventh excavation slope possible sliding surface acquisition unit is used to generate a rectangular coordinate system based on the same vertical plane; the eighth excavation slope possible sliding surface acquisition unit is used to convert all valid intersection points into coordinate points according to the rectangular coordinate system; the ninth excavation slope possible sliding surface acquisition unit is used to obtain any two coordinate points from all coordinate points and , and the line segment Get the initial circle as the diameter , where the subscript 2 indicates the number of coordinate points in the initial circle; the tenth possible sliding surface acquisition unit of the excavation slope is used to traverse each coordinate point in turn and determine the Coordinate points Is it located in the first iteration circle? ; Eleventh excavation slope possible sliding surface acquisition unit is used if the first Coordinate points Not located in the first iteration circle Inside, the line segment The diameter of the second iteration circle is obtained ; The twelfth possible sliding surface acquisition unit of the excavation slope is used to determine the Coordinate points Is it located in the second iteration circle? In which ; The thirteenth excavation slope possible sliding surface acquisition unit is used if the Coordinate points Not located in the second iteration circle Inside, the line segment The third iteration circle is obtained as the diameter ; The fourteenth excavation slope possible sliding surface acquisition unit is used to determine the first Coordinate points Is it located in the third iteration circle? In which ; The fifteenth excavation slope possible sliding surface acquisition unit is used if the first Coordinate points Not located in the third iteration circle If inside, connect , , A triangle is formed and the circumscribed circle of the triangle is obtained. The circumscribed circle is the minimum covering circle.

[0202] Furthermore, the fill slope possible sliding surface acquisition module 8 specifically includes a first fill slope possible sliding surface acquisition submodule, a second fill slope possible sliding surface acquisition submodule, a third fill slope possible sliding surface acquisition submodule, a fourth fill slope possible sliding surface acquisition submodule, a fifth fill slope possible sliding surface acquisition submodule, and a sixth fill slope possible sliding surface acquisition submodule, which are electrically connected in sequence; the first fill slope possible sliding surface acquisition submodule is electrically connected to the excavation slope possible sliding surface acquisition module 7 and the eighth excavation deformation displacement vector acquisition submodule, and the sixth fill slope possible sliding surface acquisition submodule is electrically connected to the excavation and fill possible sliding surface sending module 9.

[0203] Among them, the first fill slope possible sliding surface acquisition submodule is used to analyze several fill deformation displacement vectors of the fill digital elevation surface through a linear time series composed of all preset time periods; the second fill slope possible sliding surface acquisition submodule is used to define all deformation displacement vectors within the same preset time period as a fill deformation displacement vector data set; the third fill slope possible sliding surface acquisition submodule is used to learn and train all fill deformation displacement vector data sets through a machine learning machine, and obtain a fill deformation displacement vector prediction data set based on a preset prediction step number; the fourth fill slope possible sliding surface acquisition submodule is used to mark the future fill deformation displacement vectors in the fill deformation displacement vector prediction data set that exceed the preset displacement threshold as fill geological deformation monitoring points; the fifth fill slope possible sliding surface acquisition submodule is used to respectively obtain the geographic coordinates of each fill geological deformation monitoring point; the sixth fill slope possible sliding surface acquisition submodule is used to obtain the fill slope possible sliding surface of the fill area based on the geographic coordinates of all fill geological deformation monitoring points.

[0204] It is worth noting that the execution contents of the first fill slope possible sliding surface acquisition submodule to the sixth fill slope possible sliding surface acquisition submodule are the same as the execution contents of the excavation deformation displacement vector acquisition module 2 to the excavation slope possible sliding surface acquisition module 7, but the execution subjects are different.

[0205] It should be noted that this embodiment is a functional module item embodiment based on the above-mentioned method embodiment. The additional contents such as the preference, expansion, limitation, and example illustration of this embodiment can be found in the above-mentioned method embodiment, and this embodiment will not be repeated herein.

[0206] In this embodiment, a plurality of excavation digital elevation surfaces and a plurality of fill digital elevation surfaces are respectively obtained in the excavation area and in the fill area through remote sensing interpretation at intervals of preset time periods; a plurality of excavation deformation displacement vectors of the excavation digital elevation surfaces are parsed through a linear time series composed of all preset time periods; all deformation displacement vectors within the same preset time period are defined as an excavation deformation displacement vector data set; all excavation deformation displacement vector data sets are learned and trained by a machine learning machine, and an excavation deformation displacement vector prediction data set is obtained based on a preset prediction step number; future excavation deformation displacement vectors in the excavation deformation displacement vector prediction data set that exceed a preset displacement threshold are marked as excavation geological deformation monitoring points; the geographic coordinates of each excavation geological deformation monitoring point are respectively obtained; the possible sliding surface of the excavation slope in the excavation area is obtained based on the geographic coordinates of all excavation geological deformation monitoring points; the above steps are repeated with all fill digital elevation surfaces as the main body to obtain the possible sliding surface of the fill slope in the fill area; and the possible sliding surface of the excavation and the possible sliding surface of the fill are sent to an external visual monitoring terminal. This embodiment analyzes the deformation characteristics of the cut and fill area through remote sensing interpretation and time series technology, and performs time series prediction on the analyzed deformation characteristics, thereby realizing the determination and prediction of potential collapse characteristics of the cut and fill. Finally, the possible sliding surface of the cut and fill is confirmed through the predicted future deformation characteristics, so that the cut and fill construction has quantitative graphic data support and the subsequent prevention and control is forward-looking. Certain prevention and control measures can be adopted before the cut and fill actually undergoes deformation and damage, thereby ensuring the safety of the cut and fill construction.

[0207] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 As shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0208] The memory 102 stores program instructions for implementing a fault detection method for an oil-immersed transformer according to any one of the above embodiments.

[0209] The processor 101 is used to execute program instructions stored in the memory 102 to perform fault detection on the oil-immersed transformer.

[0210] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having a signal processing capability. The processor 101 may 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 may be a microprocessor or the processor may also be any conventional processor, etc.

[0211] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein 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, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, tablets, etc.

[0212] In the several embodiments provided in the present 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.

[0213] In addition, each functional unit in each embodiment 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 integrated unit 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 specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for monitoring excavation and filling in a pumped-storage power station reservoir area, wherein the pumped-storage power station reservoir area is applied to a pumped-storage power station under construction in a preset area, wherein the pumped-storage power station under construction includes a preset excavation area and a filling area, and wherein: The excavation and filling monitoring method comprises: Step S1, obtaining a plurality of excavation digital elevation surfaces of the excavation area and a plurality of filling digital elevation surfaces of the filling area respectively through remote sensing interpretation at preset time intervals; Step S2, analyzing a plurality of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time series composed of all preset time periods; Step S3, defining all deformation displacement vectors within a same preset time period as an excavation deformation displacement vector data set; Step S4, learning and training all excavation deformation displacement vector data sets through a machine learning machine, and obtaining an excavation deformation displacement vector prediction data set based on a preset prediction step number; Step S5, marking the future excavation deformation displacement vectors exceeding a preset displacement threshold in the excavation deformation displacement vector prediction data set as excavation geological deformation monitoring points; Step S6, respectively obtaining the geographical coordinates of each excavation geological deformation monitoring point; Step S7, obtaining the possible sliding surface of the excavation slope in the excavation area based on the geographical coordinates of all excavation geological deformation monitoring points; Step S8, repeating steps S2 to S7 with all the fill digital elevation surfaces as the main body to obtain the possible sliding surface of the fill slope in the fill area; Step S9, sending the possible sliding surface of the cut slope and the possible sliding surface of the fill slope to an external visual monitoring terminal; Step S7, based on the geographic coordinates of all excavation geological deformation monitoring points, obtain the possible sliding surface of the excavation slope in the excavation area, including: Step S71, inputting all excavation geological deformation monitoring points into the excavation digital elevation surface; Step S72, drawing projection vector lines of each geographic coordinate based on the same vertical plane on the cut digital elevation surface; Step S73, respectively obtaining the perpendicular line of each projection vector line and obtaining all the intersection points between all the perpendicular lines; Step S74, deleting outlier points from all intersection points, and defining the remaining intersection points as valid intersection points; Step S75, obtaining the minimum covering circle of all valid intersection points; Step S76, sliding the respective perpendicular lines on each projection vector line respectively so that the minimum coverage circle reaches the minimum radius; Step S77, obtaining the center of the minimum covering circle that reaches the minimum radius and using it as the center of the possible sliding surface of the excavation slope; Step S78, defining the distance between the center of the possible sliding surface of the excavated slope and the front edge of the excavated area as the radius of the possible sliding surface of the excavated slope, and obtaining the possible sliding surface of the excavated slope.

2. The excavation and filling monitoring method according to claim 1, characterized in that: Step S2, parsing a plurality of excavation deformation displacement vectors of the excavation digital elevation surface through a linear time sequence composed of all preset time periods, including: Step S21, receiving raw SAR data of the excavation area based on all preset time periods from a satellite observation terminal; Step S22, removing atmospheric delay and orbit error from all original SAR data, and obtaining a precise SAR data based on the original SAR data; Step S23, performing differentiation on all precise SAR data of the same preset time period to obtain an interference image; Step S24, sorting all interference images based on the linear time sequence; Step S25, sequentially differentiating the interference images of adjacent preset time periods, and obtaining a differential interference pattern for every two interference images; Step S26, unwrapping the phase information of each differential interferogram to obtain all surface deformation phase data of the excavation area; Step S27, converting all surface deformation phase data into map coordinates, and fusing the data with the digital elevation model of the excavation area to obtain surface deformation coordinate data; Step S28, analyzing all surface deformation coordinate data through SBAS-InSAR to obtain all excavation deformation displacement vectors.

3. The excavation and filling monitoring method according to claim 1, characterized in that: Step S4, learning and training all vector data sets through a machine learning machine, and obtaining a cut deformation displacement vector prediction data set based on a preset prediction step number, including: Step S41, performing vector normalization processing on all vector data sets to obtain a normalized data set based on a preset time period; Step S42, dividing the current normalized data set into a training set and a validation set according to a preset ratio; Step S43, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected; Step S44, inputting the training set into the input layer, performing several trainings through the neural network model, and obtaining a root mean square error between the validation set and the current training result based on each training; Step S45, obtaining the minimum value of all root mean square errors; Step S46, obtaining a training result corresponding to the minimum value as a prediction model for excavation deformation displacement vector; Step S47: predicting an excavation deformation displacement vector prediction data set based on a preset prediction step number by using the excavation deformation displacement vector prediction model.

4. The excavation and filling monitoring method according to claim 1, characterized in that: Step S74, deleting outlier points from all intersection points, and defining the remaining intersection points as valid intersection points, including: Step S741, define the intersection data set of all intersection points ,in is the number of all intersection points; Step S742: Divide horizontally and vertically, and obtain the intersection point abscissa data set based on horizontal division , based on the vertical division, the vertical coordinate data set of the intersection is obtained ; Step S743, calculate the intersection point horizontal coordinate data set Expectations , Standard Deviation , and the intersection ordinate dataset Expectations , Standard Deviation ; Step S744, when and When is a valid intersection point; Step S745, when or When is an outlier; Step S746: Delete the intersection points determined to be outliers, and define the remaining intersection points as the valid intersection points.

5. The excavation and filling monitoring method according to claim 1, characterized in that: Step S75, obtaining the minimum covering circle of all valid intersection points, including: Step S751, generating a rectangular coordinate system based on the same vertical plane; Step S752, converting all valid intersection points into coordinate points according to the rectangular coordinate system; Step S753, obtain any two coordinate points from all coordinate points and , and the line segment Get the initial circle as the diameter , where the subscript 2 represents the number of coordinate points within the initial circle; Step S754, traverse each coordinate point in turn and determine the Coordinate points Is it located in the first iteration circle? , Coordinate points Not located in the first iteration circle If yes, execute step S755; Step S755, using line segment The diameter of the second iteration circle is obtained ; Step S756, determine Coordinate points Is it located in the second iteration circle? In which , Coordinate points There is no circle located in the second iteration If yes, execute step S757; Step S757, using line segment The third iteration circle is obtained as the diameter ; Step S758, determine Coordinate points Is it located in the third iteration circle? In which , Coordinate points Not located in the third iteration circle If yes, execute step S759; Step S759, connect , , A triangle is formed, and a circumscribed circle of the triangle is obtained, where the circumscribed circle is the minimum covering circle.

6. A system for monitoring the excavation and filling of a reservoir area of ​​a pumped storage power station, the system being applied to the method for monitoring the excavation and filling as claimed in any one of claims 1 to 5, characterized in that: The excavation and filling monitoring system comprises: A cut-fill digital elevation surface acquisition module is used to respectively acquire a plurality of cut digital elevation surfaces of the cut area and a plurality of fill digital elevation surfaces of the fill area through remote sensing interpretation at preset time intervals; A cut deformation displacement vector acquisition module is used to analyze a plurality of cut deformation displacement vectors of the cut digital elevation surface through a linear time sequence composed of all preset time periods; The excavation deformation displacement vector data set definition module is used to define all deformation displacement vectors within the same preset time period as an excavation deformation displacement vector data set; The excavation deformation displacement vector prediction data set acquisition module is used to learn and train all excavation deformation displacement vector data sets through a machine learning machine, and obtain an excavation deformation displacement vector prediction data set based on a preset prediction step number; An excavation geological deformation monitoring point marking module is used to mark the future excavation deformation displacement vector exceeding a preset displacement threshold in the excavation deformation displacement vector prediction data set as an excavation geological deformation monitoring point; A module for acquiring geographic coordinates of excavation geological deformation monitoring points, used to respectively acquire the geographic coordinates of each excavation geological deformation monitoring point; A possible sliding surface acquisition module for the excavation slope, used to acquire the possible sliding surface of the excavation slope in the excavation area based on the geographical coordinates of all excavation geological deformation monitoring points; A fill slope possible sliding surface acquisition module is used to repeatedly execute the excavation deformation displacement vector acquisition module to the excavation slope possible sliding surface acquisition module based on all fill digital elevation surfaces to obtain the fill slope possible sliding surface of the fill area; The possible sliding surface sending module of the cut and fill slope is used to send the possible sliding surface of the cut slope and the possible sliding surface of the fill slope to an external visual monitoring terminal.

7. An electronic device, characterized in that: It 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 excavation and filling monitoring method as described in any one of claims 1 to 5 is implemented.

8. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the excavation and filling monitoring method according to any one of claims 1 to 5 can be implemented.

Images