Cooperative safety evaluation method and system for dam and side slope of water conservancy project

Abstract

The invention discloses a collaborative safety evaluation method and system for a water conservancy project dam and a slope, and relates to the technical field of water conservancy project safety monitoring and evaluation, and the method comprises the steps: constructing a safety evaluation index system based on a structure overall deformation index, a seepage index, a joint crack index and a material response index; based on a safety evaluation index system, a multi-source monitoring data set is acquired, reverse modeling is performed by using a cloud model, a t-Copula function is introduced to describe a tail joint dependence structure of each index under an extreme working condition, and the overall operation state of the structure is judged by calculating a multivariable collaborative membership degree and combining a standard grade cloud picture. According to the method, the limitation on index independence hypothesis in a traditional evaluation method is broken through, the capability of identifying the collaborative instability mode under the extreme working condition is achieved, the robustness of safety evaluation and the sensitivity of early warning are remarkably improved, and the method is suitable for risk identification and intelligent diagnosis of water conservancy project dams and slopes.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring and evaluation technology for water conservancy projects, and more specifically, to a collaborative safety evaluation method and system for water conservancy dams and slopes. Background Technology

[0002] Dams and slopes in water conservancy projects are widely used in complex geological environments such as plateau mountains, high-head river basins, and other water conservancy and hydropower projects due to their advantages of strong adaptability, good seismic performance, and high construction efficiency. With the continuous development of monitoring technology, the multi-source monitoring data available for dams and slopes is becoming increasingly abundant, covering multiple dimensions such as settlement, horizontal displacement, joint or crack opening, stress and strain, seepage pressure, and seepage flow. How to accurately identify the structural operating status from these multi-source time-series data and conduct highly reliable safety assessments is a core issue in the current safety management of water conservancy projects.

[0003] In recent years, cloud models, as an uncertainty analysis tool that integrates fuzziness and randomness, have received widespread attention in the field of dam and slope safety evaluation. Cloud models quantify the distribution characteristics of indicator states through the "expectation-entropy-hyperentropy" ternary structure, and can establish a fuzzy mapping between monitoring data and safety levels, making them suitable for engineering monitoring scenarios with incomplete information and strong data volatility. However, existing cloud model safety evaluation methods still have the following key shortcomings: (1) Independent modeling of indicators, lacking related structural expression: Traditional cloud models model each monitoring indicator as an independent variable, failing to characterize the interaction relationship and statistical dependence between indicators, and making it difficult to identify the risk pattern of "multi-indicator synergistic anomaly". (2) Unable to reflect the joint instability characteristics under extreme conditions: Dam and slope instability is often not caused by the anomaly of a single variable, but by multiple monitoring quantities deviating from the normal range under extreme conditions. The linear weighting or maximum membership principle of traditional cloud models is difficult to characterize the joint anomaly trend in the tail region. (3) Insufficient modeling capability for nonlinear and multidimensional data: Under high-dimensional index systems, cloud models suffer from difficulties in parameter determination, limited dimensional expansion, and poor integration of edge distributions, making it difficult to directly construct a reliable comprehensive evaluation cloud. (4) Lack of dynamic collaborative evolution mechanism: The operating status of dams and slopes in water conservancy projects has significant time-varying and spatial coupling characteristics. Existing cloud models are mostly based on static data evaluation and lack the ability to identify the dynamic trends, change paths, and hazard expansion of monitoring time series. Therefore, although cloud models have advantages in handling uncertainty, their independent modeling, static structure, and lack of dependent modeling severely restrict their engineering applicability in multi-index collaborative analysis and extreme working condition safety evaluation. To overcome the above shortcomings, it is urgent to introduce statistical methods that can model multivariate joint distributions, capture tail dependencies, and complement and integrate with cloud models to achieve a detailed characterization of the complex operating status of dams and slopes in water conservancy projects and an accurate determination of their safety levels. Summary of the Invention

[0004] To address the aforementioned issues, the present invention aims to provide a collaborative safety evaluation technology for dams and slopes in water conservancy projects. This technology addresses technical challenges such as weakened correlation of multi-source monitoring data, insufficient ability to identify collaborative instability under extreme conditions, and poor adaptability of traditional static index independent evaluation methods to actual engineering projects.

[0005] To achieve the above technical objectives, this application provides a collaborative safety evaluation method for dams and slopes in water conservancy projects, comprising the following steps: A safety evaluation index system is constructed based on overall structural deformation indicators, seepage indicators, joint crack indicators, and material response indicators. Based on the safety evaluation index system, a multi-source monitoring dataset is obtained, and a cloud model is used for reverse modeling. The t-Copula function is introduced to characterize the tail joint dependency structure of each index under extreme conditions. By calculating the multivariate collaborative membership degree and combining it with the standard level cloud map, the overall operating status of the structure is determined.

[0006] Preferably, when acquiring the multi-source monitoring dataset, multi-source monitoring data is acquired based on structural overall deformation indicators, seepage indicators, joint crack indicators, and material response indicators. After cleaning, anomaly removal, time series completion, unified resampling, and unit dimensionless processing, the multi-source monitoring dataset is generated using sliding time windows as the unit of statistical features.

[0007] Preferably, when performing dimensionless quantization, linear minimum-maximum dimensionless quantization is used for positive indices, and reverse dimensionless quantization is used for negative indices, compressing them into a unified standard domain.

[0008] Preferably, when using the cloud model for reverse modeling, the cloud model is a normal cloud model. Based on the fuzziness and randomness of the three-parameter description system, a forward cloud generator is used to generate standard-level clouds for comparative analysis.

[0009] Preferably, when performing reverse modeling, a reverse cloud generator is used to model each type of indicator sample, extract the digital feature parameters of the cloud model, including expectation, entropy and hyperentropy, and establish the marginal membership distribution function of each indicator.

[0010] Preferably, when introducing the t-Copula function, the membership value of each indicator is obtained as input based on the marginal membership distribution function of each indicator, and the t-Copula function is constructed. The t-Copula function uses the maximum likelihood estimation method to fit the covariance matrix and degree of freedom parameters to characterize the tail co-dependency relationship between multiple indicators.

[0011] Preferably, when calculating the multivariate collaborative membership, a joint distribution function is constructed based on the tail collaborative dependency relationship between multiple indicators, and the multivariate collaborative membership of the current time window is calculated.

[0012] Preferably, when determining the overall operating status of the structure, a five-level safety level is constructed. Each level constructs a standard cloud map through a cloud model forward generator and compares it with the joint membership degree of multiple indicators to complete the level determination. The five-level safety level includes: "normal", "basically normal", "mildly abnormal", "severely abnormal" and "malignant abnormal".

[0013] Preferably, when determining the overall operating status of the structure, a sliding window is used as the basis to continuously perform safety level analysis on all time periods, generating trend curves and heat maps of risk level evolution over time, which helps to identify collaborative instability chains, local pathological development zones, and potential hazard diffusion paths.

[0014] This invention also discloses a collaborative safety evaluation system for dams and slopes in water conservancy projects, used to implement the aforementioned collaborative safety evaluation method for dams and slopes in water conservancy projects, comprising: The indicator system construction module is used to construct a safety evaluation indicator system based on overall structural deformation indicators, seepage indicators, joint crack indicators, and material response indicators. The operational status diagnosis module is used to acquire multi-source monitoring datasets based on the safety evaluation index system, perform reverse modeling using cloud models, and introduce the t-Copula function to characterize the tail joint dependency structure of each index under extreme operating conditions. By calculating the multivariate collaborative membership degree and combining it with the standard level cloud map, the overall operational status of the structure is determined.

[0015] The present invention discloses the following technical effects: This invention breaks through the limitations of the assumption of index independence in traditional evaluation methods, has the ability to identify cooperative instability modes under extreme working conditions, significantly improves the robustness of safety evaluation and the sensitivity of early warning, and is applicable to risk identification and intelligent diagnosis of dams and slopes in water conservancy projects. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the method described in this invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] like Figure 1 As shown, this invention provides a collaborative safety evaluation technology for dams and slopes in water conservancy projects. It integrates the uncertainty expression capability of cloud models with the tail correlation modeling capability of t-Copula functions, making it suitable for intelligent analysis and safety level determination of deformation monitoring data for dams and slopes in water conservancy projects. This invention uses a typical water conservancy project monitoring system as its data foundation, covering long-term continuous observation information of various monitoring quantities such as settlement, displacement, stress, strain, cracks, and seepage pressure of dam and slope structures. Based on data-driven principles, the following multi-step collaborative safety evaluation process is constructed: Step 1: Acquisition and Preprocessing of Multi-Source Monitoring Data: Based on typical water conservancy engineering dam and slope monitoring systems, representative monitoring indicators with engineering diagnostic significance are selected, including overall structural deformation indicators (such as dam or slope settlement, horizontal displacement, and triaxial earth pressure), seepage indicators (such as seepage pressure and seepage flow), joint crack indicators (such as structural joint opening and displacement), and material response indicators (such as concrete or soil stress, steel reinforcement stress, and strain). Data cleaning, missing value handling, time resampling, and dimensionless processing are performed uniformly to ensure comparability of variables with different dimensions on a unified scale. A sliding time window method is used to extract feature samples from the time series data. Let the monitoring data sequence be... If the window length is w and the step size is s, then the number of samples N that can be generated is expressed as: In the formula, T represents the total duration of the monitoring data sequence.

[0020] Each sample contains statistics within a window (such as mean, extreme values, standard deviation, etc.) for subsequent modeling.

[0021] Step 2: Cloud model reverse modeling to construct marginal distributions: For each statistical sample sequence The ternary parameters are obtained using the inverse cloud model method: expect: In the formula, n represents the amount of monitoring data; Entropy (representing discreteness): ; Hyperentropy (representing fluctuation uncertainty): ; The above parameters are used to construct the membership function for each monitoring indicator: This is used to represent the tendency of the indicator to belong to different security levels within each time window.

[0022] Step 3: Construct the t-Copula joint distribution model: using the membership value of each indicator as the input variable. By using pseudovariable mapping transformation, a multidimensional t-Copula joint distribution model is constructed: in: It is the inverse function of the t-distribution with v degrees of freedom; is the correlation coefficient matrix between variables; v is the degree of freedom parameter, obtained by fitting using the maximum likelihood estimation method (MLE).

[0023] This model can be used to calculate the joint tail dependency coefficient: In the formula, ρ represents the correlation or tail dependence strength among multiple variables; this coefficient is used to quantitatively characterize the collaborative instability potential among multiple variables under extreme conditions.

[0024] Step 4: Joint Membership Calculation and Security Level Determination: Based on the t-Copula function C, the marginal membership degrees of multiple indicators are integrated into a joint membership degree. Compare the joint membership values ​​with the standard Level 5 security level cloud map: Each level corresponds to a standard cloud model parameter. Let represent expectation, entropy, and hyperentropy, respectively. The choice is... The level with the closest membership degree : Output level This serves as the security level evaluation result for that time window.

[0025] Step 5: Rolling Risk Trend Analysis and Collaborative Early Warning Output: Based on a sliding window, continuous safety level analysis is performed across all time periods to generate trend curves and heatmaps showing the evolution of risk levels over time. This helps identify collaborative instability chains, localized abnormal development zones, and potential hazard propagation paths. A real-time early warning mechanism is supported when the risk level exceeds a preset threshold (e.g., "severe anomaly").

[0026] The t-Copula-cloud model collaborative security evaluation method proposed in this invention has the following characteristics: Feature 1: This invention breaks through the strong dependence of traditional methods on the independence of indicators, and can systematically integrate multiple types of monitoring information, enhancing the expressive dimension of the model: This invention no longer requires that the monitoring indicators be independent of each other, but explicitly describes the statistical dependency structure between indicators through the Copula function, so that the evaluation system can simultaneously accept more dimensions of observation data (the recommended indicator dimension can be extended to 50 dimensions, covering all monitoring methods of various parts of the dam, such as settlement, horizontal displacement, seepage pressure, stress, strain, and crack opening, etc.), improving the integrity and scalability of the safety evaluation model, and is suitable for the data fusion needs under the high-density monitoring network of the dam.

[0027] Feature 2: This invention utilizes the t-Copula function to construct multi-indicator synergistic relationships, achieving joint risk modeling under complex operating conditions. Traditional methods often employ weighted summation, fuzzy synthesis, or grey relational analysis to synthesize multiple indicators, failing to reflect the dynamic coupling and joint evolution relationships between indicators. This invention, based on a joint distribution modeling mechanism using the t-Copula function, can accurately characterize the synergistic change features of different monitoring quantities under extreme conditions, effectively distinguishing between "local anomalies" and "global synergistic instability," and enhancing the model's physical interpretation capability of actual deformation mechanisms.

[0028] Feature 3: This invention introduces a tail-dependent structure modeling mechanism to enhance anomaly identification and early warning capabilities under extreme conditions: The t-Copula function naturally possesses the ability to characterize collaborative anomalies in the tails of variables. By calculating the tail correlation coefficient (λ), the probability of multiple indicators simultaneously exhibiting anomalies under extreme conditions can be quantitatively reflected. This is of great value for identifying nonlinear instability modes such as slippage, voiding, and seepage channel formation. This method significantly improves the early warning sensitivity for potential catastrophic stages without sacrificing the accuracy of normal state identification.

[0029] Feature 4: The joint membership evaluation method designed in this invention enhances the robustness and sensitivity of security determination: This invention constructs a joint membership function ( This method replaces the traditional "maximum membership principle" or "weighted synthesis," and can still stably output the safety level when the fluctuations of various indicators are inconsistent and the data quality is uneven. It significantly improves the model's adaptability to noise interference, sporadic anomalies, and complex evolution trends, and is suitable for the comprehensive evaluation of uncertainties in water conservancy dams and slopes.

[0030] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0031] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0032] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A collaborative safety evaluation method for dams and slopes in water conservancy projects, characterized in that, Includes the following steps: A safety evaluation index system is constructed based on overall structural deformation indicators, seepage indicators, joint crack indicators, and material response indicators. Based on the aforementioned safety evaluation index system, a multi-source monitoring dataset is obtained, and reverse modeling is performed using a cloud model. The t-Copula function is introduced to characterize the tail joint dependency structure of each index under extreme operating conditions. By calculating the multivariate collaborative membership degree and combining it with the standard level cloud map, the overall operating status of the structure is determined.

2. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 1, characterized in that: When acquiring the multi-source monitoring dataset, multi-source monitoring data is acquired based on structural overall deformation indicators, seepage indicators, joint crack indicators, and material response indicators. After cleaning, anomaly removal, time series completion, unified resampling, and unit dimensionless processing, the multi-source monitoring dataset is generated using sliding time windows as the unit of statistical features.

3. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 2, characterized in that: When performing dimensionless quantization, linear minimum-maximum dimensionless quantization is used for positive indices, and reverse dimensionless quantization is used for negative indices, compressing them into a unified standard domain.

4. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 3, characterized in that: When using a cloud model for reverse modeling, the cloud model is a normal cloud model. Based on the fuzziness and randomness of the three-parameter description system, a forward cloud generator is used to generate standard-level clouds for comparative analysis.

5. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 4, characterized in that: When performing reverse modeling, a reverse cloud generator is used to model each type of indicator sample, extract the digital feature parameters of the cloud model, including expectation, entropy and hyperentropy, and establish the marginal membership distribution function of each indicator.

6. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 5, characterized in that: When introducing the t-Copula function, the membership value of each indicator is obtained as input based on the marginal membership distribution function of each indicator, and the t-Copula function is constructed. The t-Copula function uses the maximum likelihood estimation method to fit the covariance matrix and degree of freedom parameters to characterize the tail co-dependency among multiple indicators.

7. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 6, characterized in that: When calculating the multivariate co-membership, a joint distribution function is constructed based on the tail co-dependency among multiple indicators to calculate the multi-indicator joint membership for the current time window.

8. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 7, characterized in that: When determining the overall operational status of the structure, a five-level safety system is constructed. Each level constructs a standard cloud map through a cloud model forward generator and compares it with the joint membership degree of multiple indicators to complete the level determination. The five-level safety system includes: "normal", "basically normal", "mildly abnormal", "severely abnormal" and "malignant abnormal".

9. The collaborative safety evaluation method for dams and slopes in water conservancy projects according to claim 8, characterized in that: When determining the overall operational status of the structure, a sliding window is used as the basis to continuously analyze the safety level over all time periods, generating trend curves and heat maps of risk level evolution over time, which helps to identify collaborative instability chains, local pathological development zones, and potential hazard diffusion paths.

10. A collaborative safety evaluation system for dams and slopes in water conservancy projects, used to implement the collaborative safety evaluation method for dams and slopes in water conservancy projects as described in claim 1, characterized in that, include: The indicator system construction module is used to construct a safety evaluation indicator system based on structural overall deformation indicators, seepage indicators, joint crack indicators, and material response indicators. The operational status diagnosis module is used to obtain multi-source monitoring datasets based on the safety evaluation index system, perform reverse modeling using a cloud model, and introduce a t-Copula function to characterize the tail joint dependency structure of each index under extreme operating conditions. By calculating the multivariate collaborative membership degree and combining it with the standard level cloud map, the overall operational status of the structure is determined.

Images