Slope Monitoring Method and System Based on Multi-parameter Fusion

Abstract

The present invention relates to the field of slope monitoring technology, and specifically to a slope monitoring method and system based on multi-parameter fusion. The system discloses a multi-parameter slope monitoring module, a basic instability fusion evaluation module, an evolutionary instability fusion evaluation module, and a comprehensive instability warning module. By setting the multi-parameter slope monitoring module and the basic instability fusion evaluation module, the current instability risk of the slope is regularly analyzed based on a multi-parameter fusion method, and various monitoring parameters of the slope are predicted in combination with an LSTM model. In combination with finite element analysis software, a slope analysis model is constructed, and an in-depth simulation analysis is performed on the influence of each prediction parameter on the evolution of other monitoring parameters. The key action points and conduction paths of each parameter in the slope instability process can be revealed, and the comprehensive instability warning level of the slope can be comprehensively determined. The slope monitoring and stability evaluation process is optimized from multiple levels, allowing decision makers to have a more comprehensive and in-depth understanding of the instability risk of the slope.

Description

Technical Field

[0001] The present invention relates to the technical field of slope monitoring, and more particularly to a slope monitoring method and system based on multi-parameter fusion. Background Art

[0002] In numerous engineering construction and natural slope maintenance scenarios, slope stability plays a vital role in ensuring the safety of surrounding personnel, protecting infrastructure, and preserving the ecological environment. With the increasing scale and complexity of slope engineering projects, accurate, comprehensive, and timely monitoring and assessment of slope stability has become a critical issue that needs to be addressed.

[0003] Traditional slope monitoring methods often focus on monitoring and analyzing a single or a few parameters. A common example is focusing solely on surface displacement parameters, measuring the displacement of the slope surface using equipment such as total stations and GPS receivers to determine whether the slope is stable. However, slope stability is actually the result of the interaction of multiple complex factors, and relying solely on a single parameter cannot fully reflect the true stability of the slope. For example, even if the surface displacement does not change significantly in the short term, an abnormal rise in the groundwater level may be gradually weakening the shear strength of the slope soil, or the concentrated accumulation of stress within the rock and soil may be quietly changing the mechanical equilibrium of the slope. These potential destabilizing factors cannot be detected from surface displacement parameters alone, which can easily lead to misjudgment of slope stability and miss the best opportunity for prevention and control.

[0004] Furthermore, some traditional methods that employ multi-parameter monitoring also have numerous shortcomings. Most of these methods simply list individual monitoring parameters, lacking in-depth analysis of the inherent connections and interactions between them. The data for each parameter is relatively isolated, making it difficult to accurately reveal the complex physical and mechanical processes within the slope and the dynamic influence mechanisms among these factors. For example, when multiple parameters such as groundwater level, stress, and vibration vary simultaneously, it is difficult to determine how these factors interact and contribute to slope stability, making it impossible to accurately assess the actual risk of slope instability under different working conditions.

[0005] Furthermore, traditional stability assessments are mostly static, analyzing only the slope's state at a specific point in time and lacking the ability to predict future stability trends. This forces decision-makers to base slope maintenance and management strategies on the current situation, making it difficult to plan countermeasures in advance and resulting in a relatively passive response to potential slope instability risks.

[0006] In view of the many shortcomings of the above-mentioned traditional slope monitoring methods, stability assessment means and early warning mechanisms, there is an urgent need for an innovative slope monitoring method and system that can comprehensively consider multiple parameters and their interactions, so as to achieve accurate and dynamic assessment of slope stability and scientific and reasonable early warning. Summary of the Invention

[0007] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a slope monitoring method and system based on multi-parameter fusion.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The slope monitoring system based on multi-parameter fusion includes a multi-parameter slope monitoring module, a foundation instability fusion evaluation module, an evolutionary instability fusion evaluation module, and a comprehensive instability warning module;

[0010] The multi-parameter slope monitoring module collects various monitoring parameters associated with the slope in real time;

[0011] The foundation instability fusion evaluation module regularly determines the parameter characteristics of various monitoring parameters, and then determines the foundation instability evaluation index of the slope;

[0012] The evolutionary instability fusion evaluation module, after determining the basic instability evaluation index of the slope, simultaneously determines the time series prediction characteristics of various monitoring parameters, constructs a slope analysis model, obtains the parameter linkage influence index of various monitoring parameters, and then determines the evolutionary instability evaluation index of the slope;

[0013] The comprehensive instability warning module determines the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

[0014] Furthermore, the parameter characteristics of the monitoring parameters are determined as follows: a type of monitoring parameters is selected, all data of the type of monitoring parameters in a period are obtained, the data of the monitoring parameters are preprocessed and feature extracted, and the parameter characteristics of the monitoring parameters are extracted.

[0015] Furthermore, the foundation instability evaluation index of the slope is determined as follows: the parameter characteristics of various monitoring parameters are combined into a parameter feature set in the form of a feature set, a foundation instability evaluation model is selected, the parameter feature set is input into the foundation instability evaluation model, and the foundation instability evaluation model outputs the foundation instability evaluation index of the slope.

[0016] Furthermore, the time series prediction characteristics of the monitoring parameters are determined as follows: select a type of monitoring parameters, obtain the parameter characteristics of the monitoring parameters in the previous j periods, combine the parameter characteristics of the j periods into a parameter time series feature set in the form of a feature set, select the parameter time series prediction model corresponding to this type of monitoring parameters, input the parameter time series feature set into the parameter time series prediction model, and the parameter time series prediction model outputs the time series prediction characteristics of the monitoring parameters.

[0017] Furthermore, the parameter linkage influence index of the monitoring parameters is obtained as follows: select a type of monitoring parameters, obtain the time series prediction characteristics of this type of monitoring parameters, mark the remaining types of monitoring parameters as evolution influencing parameters, obtain the parameter characteristics of each evolution influencing parameter, synchronously input the time series prediction characteristics of this type of monitoring parameters and the parameter characteristics of each evolution influencing parameter into the slope analysis model, and perform a cycle of simulation on the slope analysis model. After the simulation, obtain the simulation parameter characteristics of each evolution influencing parameter in the slope analysis model, combine the simulation parameter characteristics and parameter characteristics of the same evolution influencing parameters into a feature comparison group, obtain the feature evolution comparison model corresponding to each evolution influencing parameter, input the feature comparison group of each evolution influencing parameter into the corresponding feature evolution comparison model, obtain the evolution anomaly index of each evolution influencing parameter, obtain the number of times the evolution anomaly has intensified, and obtain the parameter linkage influence index of the monitoring parameters based on the evolution anomaly index of each evolution influencing parameter and the number of times the evolution anomaly has intensified.

[0018] Furthermore, the number of times the evolution anomaly is aggravated is obtained as follows: an evolution anomaly threshold index is set, and when the evolution anomaly index of the evolution influencing parameter is greater than the evolution anomaly threshold index, the number of times the evolution anomaly is aggravated is increased by one.

[0019] Furthermore, the evolutionary instability evaluation index of the slope is determined as follows: the parameter linkage influence index of each monitoring parameter is summed and averaged to obtain the average parameter linkage influence index, the number of linkage promotions is obtained, and the evolutionary instability evaluation index of the slope is determined based on the average parameter linkage influence index and the number of linkage promotions.

[0020] Furthermore, the acquisition process of the number of linkage promotions is as follows: compare each type of monitoring parameters in pairs, calculate the sum of the parameter linkage influence indexes of the two types of compared monitoring parameters, calculate the linkage promotion sum index, set the linkage promotion sum threshold index, and when the linkage promotion sum index is greater than the linkage promotion sum threshold index, increase the number of linkage promotions by one.

[0021] Furthermore, the slope monitoring method based on multi-parameter fusion includes the following steps:

[0022] Step 1: Regularly determine the parameter characteristics of various monitoring parameters, and then determine the foundation instability evaluation index of the slope;

[0023] Step 2: Determine the time series prediction characteristics of various monitoring parameters, build a slope analysis model, obtain the parameter linkage influence index of various monitoring parameters, and then determine the slope evolution instability evaluation index;

[0024] Step 3: Determine the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. The method of the present invention can reveal the key points and transmission paths of various parameters in the process of slope instability, and then comprehensively determine the comprehensive instability warning level of the slope. It optimizes the slope monitoring and stability assessment process from multiple levels, allowing decision makers to have a more comprehensive and in-depth understanding of the slope instability risk;

[0027] 2. The system of the present invention sets a multi-parameter slope monitoring module and a basic instability fusion evaluation module, regularly analyzes the current instability risk of the slope based on a multi-parameter fusion method, and predicts various monitoring parameters of the slope in combination with the LSTM model. Combined with finite element analysis software, a slope analysis model is constructed, and an in-depth simulation is performed to analyze the impact of each prediction parameter on the evolution of the remaining monitoring parameters, intuitively presenting the dynamic interaction mechanism between the monitoring parameters, and more comprehensively understanding the actual impact of each prediction parameter on the slope stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flowchart of the slope monitoring method based on multi-parameter fusion;

[0029] Figure 2 This is the principle block diagram of the slope monitoring system based on multi-parameter fusion;

[0030] Figure 3 A flow chart for determining time series prediction characteristics of monitoring parameters;

[0031] Figure 4 Flowchart for determining the foundation instability evaluation index of the slope. DETAILED DESCRIPTION

[0032] Example 1: Reference Figure 1 ,The slope monitoring method based on multi-parameter fusion includes the following steps:

[0033] Step 1: Regularly determine the parameter characteristics of various monitoring parameters, and then determine the foundation instability evaluation index of the slope;

[0034] Step 2: Determine the time series prediction characteristics of various monitoring parameters, build a slope analysis model, obtain the parameter linkage influence index of various monitoring parameters, and then determine the slope evolution instability evaluation index;

[0035] Step 3: Determine the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

[0036] Example 2: Reference Figures 2 to 4 The slope monitoring system based on multi-parameter fusion includes a multi-parameter slope monitoring module, a foundation instability fusion evaluation module, an evolution instability fusion evaluation module, and a comprehensive instability early warning module.

[0037] The above method can reveal the key points of action and transmission paths of various parameters in the process of slope instability, and then comprehensively determine the comprehensive instability warning level of the slope. It optimizes the slope monitoring and stability assessment process from multiple levels, allowing decision makers to have a more comprehensive and in-depth understanding of the instability risk of the slope.

[0038] The multi-parameter slope monitoring module collects various monitoring parameters related to the slope in real time (types of monitoring parameters include surface displacement parameters, stress parameters, groundwater level parameters, vibration parameters, etc.).

[0039] The foundation instability fusion evaluation module regularly determines the parameter characteristics of various monitoring parameters, and then determines the foundation instability evaluation index of the slope .

[0040] The parameter characteristics of the monitoring parameters are determined as follows: select a type of monitoring parameters, obtain all data of this type of monitoring parameters within a period, preprocess the data of the monitoring parameters and extract features (preprocessing methods include outlier processing, missing value processing, denoising processing, normalization processing, etc., and feature extraction methods include time domain feature extraction, frequency domain feature extraction, etc.), and extract the parameter characteristics of the monitoring parameters.

[0041] The foundation instability evaluation index of the slope is determined as follows: the parameter characteristics of various monitoring parameters are combined into a parameter feature set in the form of a feature set, a foundation instability evaluation model is selected, the parameter feature set is input into the foundation instability evaluation model, and the foundation instability evaluation model outputs the foundation instability evaluation index of the slope.

[0042] The construction process of the foundation instability evaluation model is as follows: construct a neural network model, collect i parameter feature sets, train the neural network model through the parameter feature sets, and assign a foundation instability evaluation index to each parameter feature set. The index range of the foundation instability evaluation index is (1.0~15.0). The larger the foundation instability evaluation index, the greater the current instability hazard of the slope. The training data is divided into training set, validation set and test set in a ratio of 60%:20%:20%. The neural network is iteratively trained on the training set, validation set and test set. Finally, a foundation instability evaluation model is constructed.

[0043] The evolutionary instability fusion evaluation module, after determining the basic instability evaluation index of the slope, simultaneously determines the time series prediction characteristics of various monitoring parameters, constructs a slope analysis model, obtains the parameter linkage influence index of various monitoring parameters, and then determines the evolutionary instability evaluation index of the slope.

[0044] The time series prediction characteristics of the monitoring parameters are determined as follows: select a type of monitoring parameters, obtain the parameter characteristics of the monitoring parameters in the previous j periods, combine the parameter characteristics of the j periods into a parameter time series feature set in the form of a feature set, select the parameter time series prediction model corresponding to this type of monitoring parameters, input the parameter time series feature set into the parameter time series prediction model, and the parameter time series prediction model outputs the time series prediction characteristics of the monitoring parameters.

[0045] Each monitoring parameter corresponds to a parameter time series prediction model. All parameter time series prediction models are built based on the LSTM model. The only difference between these models is the training data. The following uses the surface displacement parameter as an example to describe the construction process of the parameter time series prediction model for the surface displacement parameter. The LSTM model is constructed, and parameter time series feature sets for k surface displacement parameters are collected. The LSTM model is trained using these parameter time series feature sets. Each parameter time series feature set is assigned a time series prediction feature, which is the parameter feature that predicts the surface displacement parameter in the next cycle. The training data is divided into a training set, a validation set, and a test set in a ratio of 70%:15%:15%. The model is trained using the training set, and the model parameters are continuously adjusted to minimize the loss function. During training, the validation set is used to monitor model performance to avoid overfitting, and the test set is used to evaluate the trained model. Finally, a parameter time series prediction model for the surface displacement parameter is constructed.

[0046] The construction process of the slope analysis model is as follows: determine the type of rock and soil of the slope (through on-site geological survey, take rock and soil samples for indoor test analysis, combine the geological survey report and the experience of on-site engineers to determine whether the rock and soil of the slope is sand, clay, silt, rock or a mixture of them), rock and soil stratification (use drilling, pit exploration and other means to obtain the distribution of rock and soil at different depths of the slope, record the thickness of each layer of rock and soil, top and bottom surface elevations and the position of the interface between each layer. At the same time, collect rock and soil samples at different layers, test the physical and mechanical parameters of each layer, clarify the differences in strength, permeability and other aspects of each layer of rock and soil, and provide accurate stratification basis for subsequent modeling), geometric shape (use total station, GPS Receivers and other measuring equipment are used to accurately measure the slope's geometric dimensions such as slope length, slope height, slope angle, etc., to determine the overall shape and spatial range of the slope). Finite element analysis software (such as ABAQUS, ANSYS, etc.) is selected to draw the three-dimensional geometric contour of the slope in the finite element analysis software according to the geometric form of the slope. Based on the collected rock and soil type and the physical and mechanical parameters of each layer, the corresponding material models and parameters are defined for different rock and soil parts in the material property setting module of the software. For example, for sandy soil, an appropriate constitutive model (such as the Mohr-Coulomb model) is selected, and parameters such as the sand's density, internal friction angle, cohesion, elastic modulus, and Poisson's ratio are input. For different layers of soil, parameters derived from actual testing are assigned to each layer to ensure that the material properties in the model match the actual slope's soil characteristics. In the software's meshing module, the slope's geometric model is divided by selecting an appropriate mesh type (such as triangular or quadrilateral elements for 2D models, or tetrahedral or hexahedral elements for 3D models) and mesh size based on the model's complexity and computational accuracy requirements. Furthermore, at key locations such as interfaces between different soil layers and stress concentration areas, appropriate boundary conditions are set within the software based on the actual slope's boundary conditions. For example, at the bottom of the slope, fixed constraint boundaries are typically set to restrict horizontal and vertical displacement, simulating the fixed relationship between the bottom soil and the foundation in reality. For the sides of the slope, appropriate normal constraints or friction contact conditions are set based on the actual constraints of the surrounding soil. If the slope is subject to external loads (such as loads from buildings on the top of the slope, traffic loads, etc.), load boundary conditions are set at the corresponding locations by applying pressure, concentrated force, etc.; for groundwater boundaries, if they are close to water sources, corresponding head boundary conditions are set to simulate the recharge or discharge of groundwater, ensuring that the boundary conditions of the model can truly reflect the actual force and constraint state of the slope, and construct a slope analysis model.

[0047] The parameter linkage influence index of the monitoring parameters is obtained as follows: select a type of monitoring parameters, obtain the time series prediction characteristics of this type of monitoring parameters, mark the remaining types of monitoring parameters as evolution influence parameters (for example, if the surface displacement parameters are selected, obtain the time series prediction characteristics of the surface displacement parameters, and mark all monitoring parameters except the surface displacement parameters as evolution influence parameters), obtain the parameter characteristics of each evolution influence parameter, and synchronously input the time series prediction characteristics of this type of monitoring parameters and the parameter characteristics of each evolution influence parameter into the slope analysis model (the slope analysis model can perform evolution simulation based on the time series prediction characteristics and parameter characteristics), simulate the slope analysis model for one cycle, and after the simulation is completed, obtain the simulated parameter characteristics of each evolution influence parameter in the slope analysis model, combine the simulated parameter characteristics and parameter characteristics of the same evolution influence parameter into a feature comparison group, obtain the feature evolution comparison model corresponding to each evolution influence parameter, input the feature comparison group of each evolution influence parameter into the corresponding feature evolution comparison model, and obtain the evolution anomaly index of each evolution influence parameter , c=1, 2, ..., C-1, C, c represents the serial number of the corresponding evolution influencing parameter, C is the total number of evolution influencing parameters, and the evolution anomaly coefficient is set to , y=1, 2, …, Y-1, Y, < <…< < Each evolution anomaly coefficient corresponds to an evolution anomaly index within a range, and the value range of the evolution anomaly index includes (0, ],( , ],…,( , ],when ∈(0, ], the evolution anomaly coefficient is , set the evolution anomaly threshold index (the evolution anomaly threshold index is a preset index used for comparison with the evolution anomaly index). When the evolution anomaly index of the evolution influencing parameter is greater than the evolution anomaly threshold index, increase the number of evolution anomaly aggravation by one (when the evolution anomaly index of the evolution influencing parameter is less than or equal to the evolution anomaly threshold index, no processing is performed), and mark the number of evolution anomaly aggravation as ,pass Get the parameter linkage influence index of the monitoring parameter .

[0048] Each monitoring parameter corresponds to a feature evolution comparison model. All feature evolution comparison models are constructed based on deep learning models. The only difference in the construction of all feature evolution comparison models is the training data. Taking stress parameters as an example, the following discloses the construction process of the feature evolution comparison model of stress parameters: a deep learning model is constructed, and feature comparison groups of L stress parameters are collected. Each feature comparison group includes the simulated parameter features and parameter features of the stress parameter. The deep learning model is trained using the feature comparison groups of stress parameters. An evolution anomaly index is assigned to each stress parameter feature comparison group. The evolution anomaly index ranges from 1.0 to 5.0. The larger the evolution anomaly index, the more abnormal the simulated parameter features of the stress parameter after evolution are compared to the parameter features. The training data is divided into a training set and a validation set with a ratio of 70%:30%. The training set and validation set are trained, and finally, a feature evolution comparison model of stress parameters is constructed.

[0049] The slope evolution instability evaluation index is determined as follows: the parameter linkage influence index of each monitoring parameter is summed and averaged to obtain the average parameter linkage influence index. , compare each type of monitoring parameters in pairs, calculate the sum of the parameter linkage influence indexes of the two types of monitoring parameters, calculate the linkage promotion sum index, set the linkage promotion sum threshold index (the linkage promotion sum threshold index is a preset index used to compare with the linkage promotion sum index), when the linkage promotion sum index is greater than the linkage promotion sum threshold index, increase the number of linkage promotions by one (when the linkage promotion sum index is less than or equal to the linkage promotion sum threshold index, no processing is performed), and mark the number of linkage promotions as ,pass Calculate the slope evolution instability evaluation index .

[0050] The comprehensive instability warning module determines the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

[0051] Determine the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolution instability evaluation index of the slope: Calculate the comprehensive instability warning index , set each comprehensive instability warning index The range corresponds to a comprehensive instability warning level, the comprehensive instability warning index The range is [0, ],( , ],…,( , ], the comprehensive instability warning levels include comprehensive instability warning level 1, comprehensive instability warning level 2, ..., comprehensive instability warning level S-1, comprehensive instability warning level S, the slope instability risk of comprehensive instability warning level 2 is higher than that of comprehensive instability warning level 1, and so on.

[0052] A multi-parameter slope monitoring module and a basic instability fusion evaluation module are set up. The current instability risk of the slope is regularly analyzed based on the multi-parameter fusion method, and the various monitoring parameters of the slope are predicted in combination with the LSTM model. Combined with finite element analysis software, a slope analysis model is constructed. The influence of each prediction parameter on the evolution of the remaining monitoring parameters is deeply simulated and analyzed, and the dynamic interaction mechanism between the monitoring parameters is intuitively presented, so as to have a more comprehensive understanding of the actual impact of each prediction parameter on the slope stability.

[0053] The above formulas are all dimensionless and numerically calculated, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0054] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0055] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0057] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0059] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) 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 codes, 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.

[0060] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. The slope monitoring system based on multi-parameter fusion is characterized by: It includes multi-parameter slope monitoring module, foundation instability fusion evaluation module, evolution instability fusion evaluation module, and comprehensive instability early warning module; The multi-parameter slope monitoring module collects various monitoring parameters associated with the slope in real time; The foundation instability fusion evaluation module regularly determines the parameter characteristics of various monitoring parameters, and then determines the foundation instability evaluation index of the slope; The evolutionary instability fusion evaluation module, after determining the basic instability evaluation index of the slope, simultaneously determines the time series prediction characteristics of various monitoring parameters, constructs a slope analysis model, obtains the parameter linkage influence index of various monitoring parameters, and then determines the evolutionary instability evaluation index of the slope; The parameter linkage influence index of the monitoring parameters is obtained as follows: select a type of monitoring parameters, obtain the time series prediction characteristics of the monitoring parameters of this type, mark the remaining types of monitoring parameters as evolution influencing parameters, obtain the parameter characteristics of each evolution influencing parameter, synchronously input the time series prediction characteristics of the monitoring parameters of this type and the parameter characteristics of each evolution influencing parameter into the slope analysis model, and simulate the slope analysis model for one cycle. After the simulation, obtain the simulation parameter characteristics of each evolution influencing parameter in the slope analysis model, combine the simulation parameter characteristics and parameter characteristics of the same evolution influencing parameters into a feature comparison group, obtain the feature evolution comparison model corresponding to each evolution influencing parameter, input the feature comparison group of each evolution influencing parameter into the corresponding feature evolution comparison model, obtain the evolution anomaly index of each evolution influencing parameter, obtain the number of times the evolution anomaly is aggravated, and obtain the parameter linkage influence index of the monitoring parameters based on the evolution anomaly index of each evolution influencing parameter and the number of times the evolution anomaly is aggravated; The number of times the evolution anomaly is aggravated is obtained as follows: an evolution anomaly threshold index is set. When the evolution anomaly index of the evolution influencing parameter is greater than the evolution anomaly threshold index, the number of times the evolution anomaly is aggravated is increased by one; The slope evolution instability evaluation index is determined as follows: the parameter linkage influence index of each monitoring parameter is summed and averaged to obtain the average parameter linkage influence index, the number of linkage promotions is obtained, and the slope evolution instability evaluation index is determined based on the average parameter linkage influence index and the number of linkage promotions; The process of obtaining the number of linkage promotions is as follows: compare each type of monitoring parameter in pairs, calculate the sum of the parameter linkage impact indexes of the two types of compared monitoring parameters, calculate the linkage promotion sum index, set the linkage promotion sum threshold index, and when the linkage promotion sum index is greater than the linkage promotion sum threshold index, increase the number of linkage promotions by one; The comprehensive instability warning module determines the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

2. The slope monitoring system based on multi-parameter fusion according to claim 1 is characterized in that: The parameter characteristics of the monitoring parameters are determined as follows: a type of monitoring parameters is selected, all data of this type of monitoring parameters in a period are obtained, the data of the monitoring parameters are preprocessed and feature extracted, and the parameter characteristics of the monitoring parameters are extracted.

3. The slope monitoring system based on multi-parameter fusion according to claim 1 is characterized in that: The foundation instability evaluation index of the slope is determined as follows: the parameter characteristics of various monitoring parameters are combined into a parameter feature set in the form of a feature set, a foundation instability evaluation model is selected, the parameter feature set is input into the foundation instability evaluation model, and the foundation instability evaluation model outputs the foundation instability evaluation index of the slope.

4. The slope monitoring system based on multi-parameter fusion according to claim 1 is characterized in that: The time series prediction characteristics of the monitoring parameters are determined as follows: select a type of monitoring parameters, obtain the parameter characteristics of the monitoring parameters in the previous j periods, combine the parameter characteristics of the j periods into a parameter time series feature set in the form of a feature set, select the parameter time series prediction model corresponding to this type of monitoring parameters, input the parameter time series feature set into the parameter time series prediction model, and the parameter time series prediction model outputs the time series prediction characteristics of the monitoring parameters.

5. A slope monitoring method based on multi-parameter fusion, applied to a slope monitoring system based on multi-parameter fusion according to any one of claims 1 to 4, characterized in that: The steps include: Step 1: Regularly determine the parameter characteristics of various monitoring parameters, and then determine the foundation instability evaluation index of the slope; Step 2: Determine the time series prediction characteristics of various monitoring parameters, build a slope analysis model, obtain the parameter linkage influence index of various monitoring parameters, and then determine the slope evolution instability evaluation index; Step 3: Determine the comprehensive instability warning level of the slope based on the basic instability evaluation index and the evolutionary instability evaluation index of the slope.

Images