Prediction and evaluation method of breakwater's strong earthquake resistance performance based on data analysis

Through the construction of finite element analysis and dynamic model, prediction evaluation coefficients are generated, which solves the problem of uncertainty in soil characteristics in the prediction of strong seismic performance of breakwater, improves prediction accuracy, and reduces the probability of dangerous events.

CN118446035BActive Publication Date: 2024-11-15FISHERY ENG RES INST CHINESE ACAD OF FISHERY SCI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410139289.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-01
Publication Date
2024-11-15
Estimated Expiration
2044-02-01

AI Technical Summary

Technical Problem

The prior art in the prediction of strong seismic performance of breakwaters, due to soil characteristics uncertainty and complex soil-structure interaction, the prediction accuracy decreases, increasing the probability that prediction inaccuracy leads to dangerous events.

Method used

By obtaining data related to the strong earthquake resistance of the breakwater, finite element analysis and dynamic model construction, obtaining model iteration information and performance sensitive information, generating prediction evaluation coefficients, determining the prediction status of the strong earthquake resistance of the breakwater, and managing to improve predictions Accuracy of the assessment.

Benefits of technology

It improves the accuracy of prediction of strong earthquake resistance performance of the breakwater, and reduces the probability of dangerous events caused by prediction inaccuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118446035B_ABST
    Figure CN118446035B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for predicting and evaluating the strong earthquake resistance performance of a breakwater based on data analysis, and relates to the technical field of breakwater seismic prediction. The method comprises the following steps: first, obtaining and recording the relevant data of the breakwater's strong earthquake resistance, performing simulation calculations through finite element analysis, selecting a dynamic model for the dynamic response of the structure, determining the strong earthquake resistance performance, and constructing a model, obtaining the prediction operation information generated during the prediction and analysis of the breakwater's strong earthquake resistance performance, the prediction operation information includes model iteration information and performance sensitivity information, generating prediction evaluation coefficients from the model iteration information and performance sensitivity information, and determining the prediction of the breakwater's strong earthquake resistance performance, and managing according to the prediction of the breakwater's strong earthquake resistance performance, thereby increasing the accuracy of the prediction evaluation and reducing the probability of dangerous events caused by inaccurate predictions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of breakwater seismic prediction, and in particular to a method for predicting and evaluating the strong earthquake resistance performance of a breakwater based on data analysis. Background Art

[0002] A breakwater is a building or structural engineering that is usually used to protect coastlines, ports, estuaries and other water areas from erosion and damage caused by hydrodynamic forces such as waves, tides and floods. The main function of a breakwater is to reduce the impact of waves, reduce the risk of coastal erosion and provide good port and water conditions.

[0003] The existing technology has the following shortcomings: breakwaters are usually built on soil, and the dynamic response of the soil has a significant impact on the seismic performance of the structure. The uncertain soil properties and complex soil-structure interactions introduce certain uncertainties in the prediction of strong earthquake resistance. Under the action of strong earthquakes, the behavior of structures and soils may become nonlinear, including inelastic deformation of materials, nonlinear vibration of structures, uncertainty in the frequency spectrum and time history of dynamic loads generated by earthquakes, etc., and because of the random nature of earthquakes themselves, it is more likely to lead to a decrease in the accuracy of strong earthquake resistance predictions.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting and evaluating the strong earthquake resistance of a breakwater based on data analysis, by obtaining relevant data on the breakwater's strong earthquake resistance and recording the data, performing simulation calculations through finite element analysis, selecting a dynamic model for the dynamic response of the structure, determining the strong earthquake resistance performance, and constructing a model, obtaining the prediction operation information generated during the prediction and analysis of the breakwater's strong earthquake resistance performance, the prediction operation information includes model iteration information and performance sensitivity information, generating prediction evaluation coefficients using the model iteration information and performance sensitivity information, and determining the prediction of the breakwater's strong earthquake resistance performance, and managing the method based on the prediction of the breakwater's strong earthquake resistance performance, thereby increasing the accuracy of the prediction and evaluation and reducing the probability of dangerous events caused by inaccurate predictions, so as to address the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for predicting and evaluating the strong earthquake resistance performance of a breakwater based on data analysis, comprising the following steps:

[0007] Before predicting the anti-seismic performance of the breakwater, obtain the relevant data on the anti-seismic performance of the breakwater and record the data;

[0008] Obtain the natural frequency and damping ratio of the breakwater structure, perform simulation calculations through finite element analysis, select a dynamic model to perform dynamic response of the structure, determine the strong earthquake resistance performance, and construct the model;

[0009] Obtaining the prediction operation information generated during the prediction analysis of the breakwater's strong earthquake resistance performance, the prediction operation information includes model iteration information and performance sensitivity information;

[0010] The model iteration information and performance sensitivity information are used to generate prediction evaluation coefficients and determine the prediction of the breakwater's strong earthquake resistance performance, and management is carried out based on the prediction of the breakwater's strong earthquake resistance performance.

[0011] Preferably, simulation calculation is performed through finite element analysis, and a dynamic model is selected to perform dynamic response of the structure to determine the earthquake resistance performance, including:

[0012] Create or import the geometric model of the breakwater in finite element analysis software, which includes the three-dimensional shape, size, and material of the structure;

[0013] Divide the structural geometry model into a finite element mesh;

[0014] Specify the corresponding material properties for each finite element, including elastic modulus, Poisson's ratio, and density;

[0015] Apply earthquake or other dynamic loads to determine boundary conditions and loading situations for analysis;

[0016] Select elastic single-degree-of-freedom model or multi-degree-of-freedom model to simulate the dynamic response of the structure, and use the earthquake response spectrum or earthquake time history to simulate and determine the strong earthquake resistance performance.

[0017] Preferably, the model iteration information includes a residual convergence stability index, and the performance sensitivity information includes a structural input response sensitivity value.

[0018] Preferably, the logic for obtaining the residual convergence stability index is as follows:

[0019] Get each time step in the iteration time period T, and obtain the model for predictive finite element analysis, which is the stress update number GX and the current stress YL now , elastic-plastic tangent stiffness tensor D, plastic strain increment SX, calculate stress update value: YL = GX*(YL now +D*SX), at each time step, the tangent stiffness matrix is ​​constructed, and the strain ε is calculated through the current stress state and elastic stiffness matrix el , calculate the partial derivatives of the stress vector and the strain vector to obtain the tangent stiffness matrix, the calculation formula is: Get the residual vector R = fe-fi, where fe is the force vector caused by external loading, fi is the force vector caused by internal stress, and get the stress increment YLadd , calculate the residual convergence stability index, the calculation expression is: CAS = (R + YK * SX - YL add ) / YL.

[0020] Preferably, the logic for obtaining the structure input response sensitivity value is as follows:

[0021] Get the number of parameters n that affect the structural performance, and get the corresponding response prediction value after parameter training And the true value of the response XY i , calculate the response variable value based on the true response value and the predicted response value: The calculation formula of the response sensitivity value based on the response variable value and the true value of the response is: The structural input response sensitivity value is calculated based on the mean square error value and the absolute error value, and the calculation expression is: JGX=(LM+BL) / (LM*BL).

[0022] Preferably, the model iteration information and the performance sensitivity information are used to generate a prediction evaluation coefficient and determine the prediction of the strong earthquake resistance performance of the breakwater. The specific steps include:

[0023] The obtained residual convergence stability index and structural input response sensitivity value are used to generate prediction evaluation coefficients;

[0024] Comparing the generated prediction evaluation coefficient with the prediction evaluation threshold;

[0025] If the prediction evaluation coefficient is greater than the prediction evaluation threshold, a prediction analysis stability signal is generated;

[0026] If the prediction evaluation coefficient is less than or equal to the prediction evaluation threshold, an abnormal fluctuation signal is generated to notify personnel for management.

[0027] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0028] The present invention obtains relevant data on the breakwater's strong earthquake resistance and records the data, performs simulation calculations through finite element analysis, selects a dynamic model to perform dynamic response of the structure, determines the strong earthquake resistance performance, and constructs a model to obtain predictive operation information generated during the predictive analysis of the breakwater's strong earthquake resistance performance. The predictive operation information includes model iteration information and performance sensitivity information. The model iteration information and performance sensitivity information are used to generate predictive evaluation coefficients and the prediction of the breakwater's strong earthquake resistance performance is determined. Management is performed based on the predicted situation of the breakwater's strong earthquake resistance performance, thereby increasing the accuracy of the predictive evaluation and reducing the probability of dangerous events caused by inaccurate predictions. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0030] Figure 1 The present invention is a flow chart of the method for predicting and evaluating the strong earthquake resistance performance of breakwaters based on data analysis. DETAILED DESCRIPTION

[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0032] Embodiment 1: The present invention provides Figure 1 The method for predicting and evaluating the strong earthquake resistance performance of a breakwater based on data analysis shown in the figure comprises the following steps:

[0033] Before predicting the anti-seismic performance of the breakwater, obtain the relevant data on the anti-seismic performance of the breakwater and record the data;

[0034] Obtain the natural frequency and damping ratio of the breakwater structure, perform simulation calculations through finite element analysis, select a dynamic model to perform dynamic response of the structure, determine the strong earthquake resistance performance, and construct the model;

[0035] Obtaining the prediction operation information generated during the prediction analysis of the breakwater's strong earthquake resistance performance, the prediction operation information includes model iteration information and performance sensitivity information;

[0036] The model iteration information and performance sensitivity information are used to generate prediction evaluation coefficients and determine the prediction of the breakwater's strong earthquake resistance performance, and management is carried out based on the prediction of the breakwater's strong earthquake resistance performance.

[0037] Breakwaters use different structural forms and materials to adapt to different water environments and engineering requirements. Breakwaters include:

[0038] A wave barrier is a straight or slightly inclined wall used to prevent waves from hitting the coastline. Wave barriers are usually built on the coastline and can be made of concrete, stone and other materials; breakwaters are long, extended structures, usually located outside the coastline, designed to slow down waves and reduce impact forces. Breakwaters can be straight, L-shaped or T-shaped, depending on the specific water area and design requirements; the design of breakwaters takes into account multiple factors such as the water environment, geological conditions, and engineering purposes. Through reasonable design and construction, breakwaters can effectively protect facilities in coastal and water areas and reduce the impact of hydrodynamic forces.

[0039] Acquire relevant data needed to predict strong earthquakes, collect design parameters of breakwater structures, including geometry, material properties, structural connection methods, etc., obtain seismic data, including historical earthquake records and seismic intensity parameters in the target area, and collect soil data, including stratigraphic information, soil type, and soil properties;

[0040] In the analysis of the collected data on the prediction of the anti-seismic performance of the breakwater, structural modeling is carried out. According to the actual geometric shape of the breakwater, a three-dimensional geometric model is established. This is completed through computer-aided design (CAD) software. It is necessary to consider the length, height, width and other dimensional parameters of the breakwater, determine the structural materials of the breakwater, including concrete, stone, steel, etc., and set the mechanical properties of the materials, such as elastic modulus, Poisson's ratio, density, etc.;

[0041] The elastic modulus is the proportional relationship between the stress and strain of a material in the elastic stage. It is used to measure the stiffness and deformation degree of a material when subjected to force. The specific formula is: E = σ / ε, where σ is the stress of the material and ε is the strain of the material. The elastic modulus is often used to describe the elastic deformation characteristics of a material when subjected to tension or compression. It is a key parameter of the mechanical properties of a material.

[0042] Poisson's ratio is the proportional relationship between the lateral contraction and longitudinal stretching of a material when it is subjected to stress. It describes the volume change of a material when it is subjected to stress. The specific formula is: v = ε tran / ε axial , where ε tran is the transverse strain, ε axial is the longitudinal strain. The value range of Poisson's ratio is usually between 0 and 0.5. For most materials, Poisson's ratio is positive. Poisson's ratio is often used to describe the deformation mode of materials when subjected to stress.

[0043] The mass distribution of the breakwater is considered in the structural model. The mass of different parts is determined according to the design specifications and structural layout. The connection mode of the internal structure of the breakwater, such as beams and supports, is considered. The constraints of the connection parts are set, including fixed supports or free supports. The natural frequency of the structure is determined, and the vibration behavior of the structure when it is excited is calculated. The natural frequency is the frequency of free vibration of the structure without external excitation. It is the natural vibration frequency of the structure and is expressed as: Where k is the stiffness of the structure and m is the mass of the structure;

[0044] Calculate the damping ratio. The damping ratio is a measure of the strength of damping in a structural vibration system. It is used to describe the degree of energy dissipation in the vibration system. The calculation formula for the damping ratio is: Where c is the damping of the structure, and the value of the damping ratio usually ranges from 0 to 1. The damping ratio of an undamped system is zero, and the damping ratio of a fully damped system is 1. The appropriate selection of the damping ratio is very important for the control and energy dissipation of structural vibration. A smaller damping ratio may lead to resonance, while a larger damping ratio can be used to reduce the vibration amplitude.

[0045] The determined natural frequency and damping ratio are simulated and calculated by finite element analysis software. The specific steps are as follows:

[0046] Prepare the structural geometry and material model, create or import the geometric model of the breakwater in the finite element analysis software, which includes the three-dimensional shape, size, material and other information of the structure;

[0047] Meshing, dividing the structural geometry model into a finite element mesh. This step involves dividing the structure into multiple small elements so that analysis can be performed on each element;

[0048] Material property settings, specify the corresponding material properties for each finite element, including elastic modulus, Poisson's ratio, density, etc. These properties are used to define the material characteristics of the structure;

[0049] Loading and boundary conditions: determine the boundary conditions and loading conditions for the analysis. For dynamic analysis, it is usually necessary to apply earthquake or other dynamic loads. At the same time, set the support conditions of the structure to prevent logical conflicts.

[0050] Select the dynamic analysis type in the finite element analysis software and use modal analysis to determine the vibration mode of the structure, including the natural frequency, vibration mode and vibration modal mass;

[0051] After setting the geometry, material properties and boundary conditions of the structure and dividing the finite element mesh, set the initial load and boundary conditions of the structure, usually zero displacement and zero velocity, select the modal analysis type in the finite element analysis software, and set relevant parameters, such as the number of calculated modes, frequency range, etc., run the modal analysis, and obtain the vibration mode of the structure. The analysis results include the natural frequency, vibration shape and vibration modal mass of each mode;

[0052] Then perform frequency response analysis. Frequency response analysis is used to study the dynamic response of the structure under external excitation, that is, the vibration behavior of the structure within a certain frequency range. Set the geometric shape, material properties and boundary conditions of the structure, divide the structure into finite element grids, set the boundary conditions of the structure, and apply external excitation (such as seismic loads or other dynamic loads). Select the frequency response analysis type in the finite element analysis software, set the frequency range of the excitation, excitation signal and other parameters, run the frequency response analysis, and obtain the response of the structure at different frequencies. The analysis results include the response characteristics of the structure's displacement, stress, etc. in the frequency domain.

[0053] Of the two types of analysis, modal analysis helps understand the vibration characteristics of a structure, while frequency response analysis provides information about how a structure responds to external excitations;

[0054] According to the complexity of the structure and the requirements of the analysis, select an appropriate structural dynamics model. For simple structures, a single-degree-of-freedom model can be used, while for complex structures, a multi-degree-of-freedom model may be required;

[0055] Determine the main vibration direction, that is, the direction in which the structure mainly vibrates under earthquake or other excitation, and select the particle position in the structure that represents the overall vibration.

[0056] Usually, the center of gravity or main mass point of the structure is selected, and an elastic single-degree-of-freedom model is established, including a mass point, a spring (representing the stiffness of the structure), and a damper (considering the damping characteristics of the structure). The actual support and fixed structure are selected in the breakwater. Then, the initial displacement and velocity conditions are defined to reflect the state of the structure before the earthquake, and the stiffness of the spring is defined to represent the stiffness of the structure. The damping ratio is set to consider the damping effect of the structure, and earthquakes or other excitations are applied to the single-degree-of-freedom system to simulate the vibration response of the structure under excitation. Modal analysis is performed to calculate the system's natural frequency, vibration mode and other dynamic parameters;

[0057] Multi-degree-of-freedom model, establish the geometric shape and material model of the structure in the finite element analysis software, perform meshing, select an appropriate number of vibration modes according to the complexity of the structure and the requirements of the analysis, and complex structures may require more vibration modes to accurately represent their dynamic response; select key nodes in the structure, define the corresponding degrees of freedom for each node, each degree of freedom represents the displacement of the structure in a certain direction, distribute the mass of the structure to each node, ensure that the mass is evenly distributed between the nodes, define the initial displacement and velocity conditions of each node, which can reflect the state of the structure before the earthquake, and then define the elastic relationship between the nodes, that is, the stiffness matrix. This reflects the stiffness characteristics of the structure. Considering the damping characteristics of the structure, the modal damping ratio or other suitable damping model can be used to apply earthquakes or other excitations to the nodes of the structure to simulate the vibration response of the structure under excitation, run dynamic analysis, calculate the response of the structure in different modes, and obtain dynamic parameters.

[0058] Select a dynamic model to understand the dynamic response of the structure, thereby evaluating its strong earthquake resistance performance, and construct a model to analyze the strong earthquake resistance performance prediction;

[0059] Introduce earthquake loads into the model, ensure that the direction and magnitude of the loads are consistent with the actual earthquake situation, and simulate through earthquake response spectrum or earthquake time history. The specific steps are as follows:

[0060] Obtain design earthquake intensity parameters, such as earthquake acceleration a, from seismological data or local building codes. Select an appropriate earthquake response spectrum, which usually includes horizontal and vertical spectra. The earthquake spectrum represents the frequency content of earthquake loads and can be obtained from seismological literature or codes. Determine the characteristic period T of the structure through structural dynamics analysis or empirical formulas provided by the code. Use the design earthquake intensity parameters and the selected earthquake spectrum to calculate the design earthquake response acceleration A. d =S(T)*a, S(T) is the earthquake spectrum acceleration amplification factor when the structural characteristic period is T. The calculation of the earthquake spectrum acceleration amplification factor S(T) usually uses the formula in the specification, for example, Where T is the characteristic period of the structure, d is the damping ratio of the structure, and g is the gravitational acceleration;

[0061] It should be noted that if it is necessary to consider the nonlinear characteristics of the structure, such as the nonlinearity of the material and the nonlinearity of the connection, these characteristics should be introduced into the model, and appropriate material constitutive relations and connection models should be used for corresponding modeling.

[0062] After completing the data input, the constructed structural model is verified and compared with the measured data or the results in the literature to ensure that the model can accurately reflect the actual situation;

[0063] The constructed model is used for predictive analysis of the anti-seismic performance of the breakwater, and the predictive operation information generated during the predictive analysis process is obtained. The predictive operation information includes model iteration information and performance sensitivity information;

[0064] The model iteration information includes the residual convergence stability index, and the performance sensitivity information includes the structural input response sensitivity value. After collection, the residual convergence stability index and the structural input response sensitivity value are calibrated as CAS and JGX respectively.

[0065] The residual convergence stability index generated when used for the prediction and analysis of the anti-seismic performance of breakwaters has an important influence on improving the prediction efficiency and accuracy. The residual convergence stability index indicates the degree of influence of the convergence speed on the model output during the nonlinear iteration process. It is used to describe the residual convergence speed and stability in the nonlinear iteration process. The residual convergence stability index has the following functions:

[0066] Iteration stability characteristics: The residual convergence stability index also provides an assessment of the stability of the nonlinear iteration process. If the index value fluctuates slightly, it indicates that the iteration is relatively stable. On the contrary, large fluctuations may indicate that the iteration process is more unstable. A stable iteration process helps to obtain reliable calculation results, while an unstable iteration may lead to calculation uncertainty.

[0067] Convergence speed analysis: The residual convergence stability index is an evaluation of the residual convergence speed during the nonlinear iteration process. A larger index value indicates that the residual convergence speed is slower and more iteration steps are required to reach a stable state. By monitoring and adjusting the residual convergence stability index, engineers can better control the iteration process to improve the convergence speed and obtain results in a shorter time.

[0068] Model accuracy: The stability and speed of the iteration process are closely related to the final model accuracy. By reasonably adjusting the iteration parameters, the residual convergence stability index can be kept in an appropriate range to maintain the accuracy of the model output. Excessive or insufficient iterations may affect the accuracy of the model, and the residual convergence stability index is an important monitoring indicator that helps to make appropriate adjustments in this balance.

[0069] Therefore, the influence of the residual convergence stability index covers multiple aspects such as convergence speed, iteration stability, computational efficiency, and model accuracy, providing engineers with a basis for optimizing the nonlinear iteration process to more effectively predict and analyze the anti-seismic performance of breakwaters;

[0070] The logic for obtaining the residual convergence stability index is as follows:

[0071] Get each time step in the iteration time period T, and obtain the model for predictive finite element analysis, which is the stress update number GX and the current stress YL now, elastic-plastic tangent stiffness tensor D, plastic strain increment SX, calculate stress update value: YL = GX*(YL now +D*SX), at each time step, the tangent stiffness matrix is ​​constructed, and the strain ε is calculated through the current stress state and elastic stiffness matrix el , calculate the partial derivatives of the stress vector and the strain vector to obtain the tangent stiffness matrix, the calculation formula is: Get the residual vector R = fe-fi, where fe is the force vector caused by external loading, fi is the force vector caused by internal stress, and get the stress increment YL add , calculate the residual convergence stability index, the calculation expression is: CAS = (R + YK * SX - YL add ) / YL.

[0072] It should be noted that the elastic-plastic tangent stiffness tensor is the local tangent stiffness of the relationship between stress and strain during the deformation process. It is used to measure the change in hardness or stiffness of the material during the deformation process. In numerical simulations such as finite element analysis, it is the basis for constructing the tangent stiffness matrix; the plastic strain increment refers to the additional strain generated in each time step when the material undergoes plastic deformation. The plastic strain is the inelastic deformation caused by the material continuing to be loaded after reaching the yield point. This deformation will not return to the initial state, but remains in the material. In the elastic-plastic material model, the plastic strain is usually related to the yield condition of the material. When the stress reaches the yield strength of the material, plastic deformation begins to occur, and the corresponding strain is the plastic strain. The plastic strain can be accumulated in each time step to consider the inelastic behavior of the material during the entire loading process. In numerical simulations such as finite element analysis, the plastic strain is considered to simulate the nonlinear behavior of the material more accurately. The elastic stiffness matrix without considering the plastic behavior refers to the stiffness matrix when the material is in a linear elastic state.

[0073] The structural input response sensitivity value generated when used for predictive analysis of the anti-seismic performance of breakwaters has an impact on the accuracy of the prediction. The structural input response sensitivity value indicates the sensitivity of the structural performance to the change of input parameters. The structural input response sensitivity value provides information about how the structural response changes with the change of input parameters, and determines the accuracy of the model's prediction of the anti-seismic performance of breakwaters. The structural input response sensitivity value affects the following aspects:

[0074] Model accuracy assessment: The structural input response sensitivity value can be used to assess the accuracy of the model. If the structure is more sensitive to changes in certain parameters, then the model may be more accurate in predicting these parameters; conversely, if the sensitivity is lower, the model needs to be modified or improved;

[0075] Identification of key parameters: By analyzing the sensitive values ​​of structural input responses, it is possible to determine which input parameters have the most significant impact on structural performance, thereby determining key parameters. Engineers can focus on the accuracy of these parameters to improve the reliability of the model;

[0076] Model correction and optimization: In actual engineering, some aspects of structural performance may be difficult to predict accurately. This may be due to the uncertainty of factors such as material properties and geometric shape. The analysis of the sensitive values ​​of structural input response can guide the correction and optimization of the model and improve the prediction accuracy of the model.

[0077] The logic for obtaining the structure input response sensitivity value is as follows:

[0078] Get the number of parameters n that affect the structural performance, and get the corresponding response prediction value after parameter training And the true value of the response XY i , calculate the response variable value based on the true response value and the predicted response value: The calculation formula of the response sensitivity value based on the response variable value and the true value of the response is: The structural input response sensitivity value is calculated based on the mean square error value and the absolute error value, and the calculation expression is: JGX=(LM+BL) / (LM*BL).

[0079] It should be noted that the parameters affecting structural performance may include material properties, geometric shapes, loads, boundary conditions, etc. The specific key parameters are selected based on actual conditions, and the number of selections is determined based on actual conditions.

[0080] The prediction of the anti-seismic performance of the breakwater is analyzed based on the model iteration information and performance sensitivity information, and the prediction accuracy of the anti-seismic performance of the breakwater is determined based on the analysis results;

[0081] The obtained residual convergence stability index and structural input response sensitivity value are used to generate the prediction evaluation coefficient, and the prediction evaluation coefficient is calibrated as YC x , based on the formula: In the formula, α and β are the preset proportional coefficients of the residual convergence stability index and the structural input response sensitivity value, respectively, and both α and β are greater than 0;

[0082] It should be noted that the formula is obtained by technicians in this field by collecting multiple groups of sample data and setting corresponding preset proportional coefficients for each group of sample data. The specific calculation process is: substituting the obtained residual convergence stability index and structural input response sensitivity value into the formula to form an equation group, and then screening and averaging the calculated preset proportional coefficients to obtain the preset proportional coefficients. Since each group of sample data is different, the specific values ​​of the preset proportional coefficients under different sample data are also different.

[0083] It can be seen from the formula that the larger the residual convergence stability index and the larger the structural input response sensitivity value, that is, the larger the performance value of the prediction evaluation coefficient, the more stable the prediction of the breakwater's strong earthquake resistance performance is, and it can produce consistent prediction results under different conditions, and it is more robust to changes in input parameters and has better reliability. The smaller the residual convergence stability index and the smaller the structural input response sensitivity value, that is, the smaller the performance value of the prediction evaluation coefficient, it is easier to have problems such as insufficient model structure, improper parameter selection, or the model does not match the actual situation, which in turn causes a decrease in the accuracy of the prediction.

[0084] A small structural input response sensitivity value means that the structural performance is not sensitive enough to the changes in the input parameters, which makes the model more robust to changes in key parameters, but it also means that the model cannot accurately capture the changes in the structure to the input parameters;

[0085] A small residual convergence stability index indicates that the residual is difficult to converge to a stable value during the iterative solution process, which is a sign that the model has numerical problems, convergence speed is too slow, or the iteration is not stable enough;

[0086] A smaller prediction evaluation coefficient may indicate that the model needs to be corrected, optimized or improved, including adjusting model parameters, increasing model complexity, improving model structure and other measures to improve model stability and accuracy. A smaller prediction evaluation coefficient may indicate that the applicability of the model is subject to certain limitations. In actual engineering applications, the limitations of the model need to be carefully considered, and other more reliable methods may need to be used for verification and prediction.

[0087] The generated prediction evaluation coefficient is compared with the prediction evaluation threshold, and an abnormal fluctuation signal and a prediction analysis stability signal are generated according to the comparison result;

[0088] After obtaining the generated prediction evaluation coefficient, the generated prediction evaluation coefficient is compared with the prediction evaluation threshold. If the prediction evaluation coefficient is greater than the prediction evaluation threshold, a prediction analysis stability signal is generated, indicating that the relevant parameters collected by the breakwater are relatively normal when predicting the strong earthquake resistance performance of the breakwater, and the model is relatively stable during prediction;

[0089] If the prediction evaluation coefficient is less than or equal to the prediction evaluation threshold, an abnormal fluctuation signal is generated, indicating that there is a problem in the monitoring of the breakwater's strong earthquake resistance performance, and timely regulation and management are required. The signal is recorded for subsequent analysis, and the corresponding alarm or notification is triggered according to the signal so that corresponding measures can be taken in time, for example, notifying relevant personnel for management.

[0090] It should be noted that the relevant threshold information in this embodiment is pre-set by professionals and will not be explained in detail here.

[0091] The present invention obtains relevant data on the breakwater's strong earthquake resistance and records the data, performs simulation calculations through finite element analysis, selects a dynamic model to perform dynamic response of the structure, determines the strong earthquake resistance performance, and constructs a model to obtain predictive operation information generated during the predictive analysis of the breakwater's strong earthquake resistance performance. The predictive operation information includes model iteration information and performance sensitivity information. The model iteration information and performance sensitivity information are used to generate predictive evaluation coefficients and the prediction of the breakwater's strong earthquake resistance performance is determined. Management is performed based on the predicted situation of the breakwater's strong earthquake resistance performance, thereby increasing the accuracy of the predictive evaluation and reducing the probability of dangerous events caused by inaccurate predictions.

[0092] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0093] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0094] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0095] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting and evaluating the strong earthquake resistance performance of breakwaters based on data analysis, characterized in that: The steps include: Before predicting the anti-seismic performance of the breakwater, obtain the relevant data on the anti-seismic performance of the breakwater and record the data; Obtain the natural frequency and damping ratio of the breakwater structure, perform simulation calculations through finite element analysis, select a dynamic model to perform dynamic response of the structure, determine the strong earthquake resistance performance, and construct the model; Obtaining the prediction operation information generated during the prediction analysis of the breakwater's strong earthquake resistance performance, the prediction operation information includes model iteration information and performance sensitivity information; Generate prediction evaluation coefficients based on model iteration information and performance sensitivity information, determine the prediction of the breakwater's strong earthquake resistance performance, and manage the breakwater based on the prediction of the breakwater's strong earthquake resistance performance; Model iteration information includes residual convergence stability index, and performance sensitivity information includes structural input response sensitivity value; The logic for obtaining the residual convergence stability index is as follows: Get each time step in the iteration time period T, and obtain the model for predictive finite element analysis, which is the stress update number GX and the current stress , elastic-plastic tangent stiffness tensor D, plastic strain increment SX, calculate stress update value: At each time step, the tangent stiffness matrix is ​​constructed and the strain is calculated using the current stress state and the elastic stiffness matrix. , calculate the partial derivatives of the stress vector and the strain vector to obtain the tangent stiffness matrix, the calculation formula is: , get the residual vector , where fe is the force vector caused by external loading and fi is the force vector caused by internal stress. , the residual convergence stability index is calculated, and the calculation expression is: ; The logic for obtaining the structure input response sensitivity value is as follows: Get the number of parameters n that affect the structural performance, and get the corresponding response prediction value after parameter training And the true value of the response , calculate the response variable value based on the true response value and the predicted response value: , the response sensitivity value calculation formula based on the response variable value and the response true value calculation parameter is: , the structural input response sensitivity value is calculated based on the mean square error value and the absolute error value, and the calculation expression is: ; The obtained residual convergence stability index and structural input response sensitivity value are used to generate the prediction evaluation coefficient, and the prediction evaluation coefficient is calibrated as , based on the formula: , where α and β are both greater than 0.

2. The method for predicting and evaluating the anti-seismic performance of breakwaters based on data analysis according to claim 1 is characterized in that: Through finite element analysis, simulation calculations are performed, and a dynamic model is selected to perform dynamic response of the structure and determine the earthquake resistance performance, including: Create or import the geometric model of the breakwater in finite element analysis software, which includes the three-dimensional shape, size, and material of the structure; Divide the structural geometry model into a finite element mesh; Specify the corresponding material properties for each finite element, including elastic modulus, Poisson's ratio, and density; Apply seismic or dynamic loads to determine boundary conditions and loading situations for analysis; Select elastic single-degree-of-freedom model or multi-degree-of-freedom model to simulate the dynamic response of the structure, and use the earthquake response spectrum or earthquake time history to simulate and determine the strong earthquake resistance performance.

3. The method for predicting and evaluating the anti-seismic performance of breakwaters based on data analysis according to claim 2 is characterized in that: The model iteration information and performance sensitivity information are used to generate prediction evaluation coefficients and determine the prediction of the breakwater's strong earthquake resistance performance. The specific steps include: The obtained residual convergence stability index and structural input response sensitivity value are used to generate prediction evaluation coefficients; Comparing the generated prediction evaluation coefficient with the prediction evaluation threshold; If the prediction evaluation coefficient is greater than the prediction evaluation threshold, a prediction analysis stability signal is generated; If the prediction evaluation coefficient is less than or equal to the prediction evaluation threshold, an abnormal fluctuation signal is generated to notify personnel for management.