Intelligent prediction method and system for stability of double-wall steel cofferdam structure

Abstract

The invention relates to the technical field of cofferdam stability prediction, and relates to a double-wall steel cofferdam structure stability intelligent prediction method and system, and the method comprises the steps: obtaining the installation position of a sensor; arranging a sensor cluster according to the mounting positions of the sensors; data are collected according to the sensor cluster, sampling information is obtained, and the sampling information comprises strain data of the double-wall steel cofferdam structure, water flow velocity data and soil mass pore water pressure data; preprocessing the sampling information to obtain preprocessed sampling information; according to the preprocessed sampling information, a preset double-wall steel cofferdam numerical model is corrected, and a corrected numerical model is obtained; according to the corrected numerical model, the stability level of the double-wall steel cofferdam structure is predicted, and a prediction result is obtained.Potential safety hazards can be found in advance, engineers are assisted to take measures in time, construction and use safety of the double-wall steel cofferdam are guaranteed, and accident risks are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cofferdam stability prediction, and in particular to a method and system for intelligently predicting the stability of a double-wall steel cofferdam structure. Background Art

[0002] As a key temporary support structure for deepwater bridges, ports and other projects, the stability of double-walled steel cofferdams directly determines the safety and efficiency of construction. Due to the complex and changeable underwater environment (such as water flow impact, wave load, foundation softening, etc.), the cofferdam may cause catastrophic accidents due to overturning, sliding or seepage instability, so accurate prediction of its stability is a core requirement for engineering safety. Existing technologies mainly predict stability through theoretical mechanical analysis (static equilibrium equation), finite element numerical simulation (fluid-solid coupling simulation) and physical model tests (water tank scale test), but the above methods are still difficult to achieve stability prediction of underwater double-walled steel cofferdam structures. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for intelligently predicting the stability of a double-walled steel cofferdam structure to improve the above-mentioned problem.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions: On the one hand, an embodiment of the present application provides a method for intelligently predicting the stability of a double-walled steel cofferdam structure, the method comprising: Get the installation location of the sensor; Arranging sensor clusters according to installation locations of the sensors; According to the data collected by the sensor cluster, sampling information is obtained, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data, and soil pore water pressure data; Preprocessing the sampling information to obtain preprocessed sampling information; The preset double-wall steel cofferdam numerical model is modified according to the preprocessed sampling information to obtain a modified numerical model; The stability grade of the double-wall steel cofferdam structure is predicted based on the modified numerical model to obtain a prediction result.

[0005] In a second aspect, an embodiment of the present application provides an intelligent prediction system for the stability of a double-walled steel cofferdam structure, the system comprising: An acquisition module, used to acquire the installation position of the sensor; A first processing module, configured to arrange a sensor cluster according to an installation position of the sensor; A second processing module is used to collect data according to the sensor cluster to obtain sampling information, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data, and soil pore water pressure data; A third processing module is used to preprocess the sampling information to obtain preprocessed sampling information; A fourth processing module is used to modify the preset double-wall steel cofferdam numerical model according to the preprocessed sampling information to obtain a modified numerical model; The prediction module is used to predict the stability level of the double-wall steel cofferdam structure according to the modified numerical model to obtain a prediction result.

[0006] In a third aspect, an embodiment of the present application provides a double-walled steel cofferdam structure stability intelligent prediction device, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the steps of the above-mentioned double-walled steel cofferdam structure stability intelligent prediction method when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for intelligent prediction of the stability of a double-walled steel cofferdam structure are implemented.

[0008] The beneficial effects of the present invention are: The present invention determines the installation position of the sensor and then installs the sensor to collect data to obtain sampling information, which solves the problem of low quality of collected data due to the complex environment in which the double-wall steel cofferdam structure is located. The data is then preprocessed and the preprocessed sampling information is used to correct the preset double-wall steel cofferdam numerical model, and a multi-physics digital twin model is established. Based on the multi-physics digital twin model, the stability level of the double-wall steel cofferdam structure is predicted in a complex underwater environment, which effectively improves the stability prediction accuracy of the double-wall steel cofferdam structure in a complex environment, discovers potential safety hazards in advance, and helps engineering personnel take measures in time to ensure the safety of construction and use of the double-wall steel cofferdam and reduce the risk of accidents.

[0009] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 It is a schematic flow chart of the intelligent prediction method for the stability of the double-walled steel cofferdam structure described in an embodiment of the present invention.

[0012] Figure 2 It is a schematic diagram of the structure of the intelligent prediction system for the stability of the double-walled steel cofferdam structure described in an embodiment of the present invention.

[0013] Figure 3 It is a schematic diagram of the structure of the intelligent prediction device for the stability of the double-walled steel cofferdam structure described in an embodiment of the present invention.

[0014] Labels in the figure: 800, intelligent prediction equipment for double-wall steel cofferdam structure stability; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, first processing module; 903, second processing module; 904, third processing module; 905, fourth processing module; 906, prediction module. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0016] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0017] Embodiment 1: This embodiment provides an intelligent prediction method for the stability of a double-walled steel cofferdam structure. It can be understood that in this embodiment, a scenario can be laid out, for example: a scenario for predicting the stability of an underwater double-walled steel cofferdam structure.

[0018] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6.

[0019] Step S1, obtaining the installation position of the sensor; The step S1 also includes step S11, step S12 and step S13, which specifically include: Step S11, obtaining the dynamic load model and the structural information of the double-walled steel cofferdam; In this step, the specific process of obtaining the dynamic load model is as follows: collect data such as water flow velocity, wave height, tidal water level, etc. around the double-walled steel cofferdam from various sensors, which include historical data and real-time data. Organize the collected data to ensure the accuracy and completeness of the data in preparation for subsequent analysis; pre-process the collected data, including but not limited to cleaning, removing outliers and noise data; build an LSTM model and use the pre-processed data to train the LSTM model to obtain a dynamic load prediction model.

[0020] Step S12, determining the load of water flow on different parts of the double-walled steel cofferdam according to the dynamic load model; In this step, the dynamic load model can capture the changing patterns of dynamic loads by learning a large amount of data, and predict parameters such as the size, direction, and frequency of water flow force, wave force, and tidal force in the future, thereby determining the impact of dynamic loads such as water flow force, wave force, and tidal force on different parts of the double-walled steel cofferdam in actual work.

[0021] Step S13: determining the installation position of the sensor according to the load of the water flow on different parts of the double-walled steel cofferdam and the structural information of the double-walled steel cofferdam.

[0022] In this step, after clarifying the loads of water flow on different parts of the double-walled steel cofferdam, the characteristics of different loads and the structural responses caused can be determined. For example, if it is predicted that the water flow force has high-frequency periodic changes in a certain direction, it can be known that the double-walled steel cofferdam structure in this direction will be subjected to large alternating stress, which belongs to the key stress-bearing area. Based on this, the key areas for sensor layout can be accurately located to avoid blind layout, making sensor monitoring more targeted and ensuring the acquisition of the most critical structural status information. At the same time, according to the structural information of the double-walled steel cofferdam, its stress concentration structural areas can also be determined, such as the connection between the inner and outer wall steel plates and the horizontal trusses and bulkheads. Due to the difference in stiffness of different components, stress concentration is prone to occur under dynamic loads; and the area close to the bottom of the riverbed not only bears large soil pressure, but is also affected by water scouring and tidal forces. Based on this, the key areas for sensor layout can also be determined.

[0023] In this embodiment, the sensor layout is optimized based on the dynamic load model and the structural information of the double-walled steel cofferdam, which can effectively improve the quality of data collection of the double-walled steel cofferdam structure in a complex underwater environment, thereby further improving the accuracy of stability prediction.

[0024] Step S2, arranging the sensor cluster according to the installation position of the sensor; In this step, the sensor cluster includes but is not limited to fiber grating strain gauges and MEMS inclinometers for structural monitoring; acoustic Doppler flowmeters and micro pressure sensors for flow field monitoring; and piezometers and distributed fiber optic temperature measurement for soil monitoring.

[0025] Step S3, collecting data according to the sensor cluster to obtain sampling information, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data, and soil pore water pressure data; Step S4, preprocessing the sampling information to obtain preprocessed sampling information; The step S4 also includes step S41, step S42 and step S43, which specifically include: Step S41, using Kalman filtering to process the water flow velocity data included in the sampling information to obtain processed first information; In this step, an adaptive Kalman filter is used to eliminate high-frequency vibration interference, specifically: (1) Construct a state space model of the double-walled steel cofferdam vibration system, define state variables including key physical quantities such as structural displacement, velocity, acceleration, and establish state equations and observation equations. Based on the original vibration signal of the sensor, output the initialization state vector and covariance matrix; (2) Enter the prediction-update cycle. The prediction stage predicts the current state and covariance based on the state at the previous moment; the update stage corrects the prediction result in combination with real-time vibration data, calculates the residual and monitors its statistical characteristics. Through iteration, the true state is gradually approached, and the filtered state estimate and residual are output; (3) When the residual variance exceeds the preset threshold, the maximum a posteriori estimation is used to optimize the noise covariance matrix online to adapt it to non-steady-state high-frequency interference and ensure the positive definiteness of the matrix. Finally, the displacement is extracted from the filtered state to complete the signal reconstruction, the high-frequency noise suppression effect is verified by frequency domain analysis, and the filter optimality is confirmed by residual whitening test, and the denoised vibration signal, i.e., the first information after processing, is output.

[0026] Step S42, using a wavelet threshold denoising method to process the soil pore water pressure data included in the sampling information to obtain processed second information; In this step, a specific implementation method is: based on the characteristics of the soil seepage pressure signal with low frequency and slow variation and random noise, the Symlets wavelet is selected to perform wavelet decomposition on the soil pore water pressure data included in the sampling information, and the low-frequency approximation coefficient and the high-frequency detail coefficient are separated; the Stein unbiased risk estimation is used to determine the global optimal threshold, and the hierarchical adaptive threshold is calculated, and the high-frequency detail coefficient is processed using the soft threshold function, the low-frequency approximation coefficient is retained, and the high-frequency component dominated by noise is suppressed to obtain the processed coefficient; the processed coefficient is subjected to inverse wavelet transform to reconstruct the signal, and the drift estimation and baseline correction are calculated by moving average to obtain the denoised and drift-free soil pore water pressure signal. It should be noted that the calculation of the hierarchical adaptive threshold is specifically as follows: ; In the above formula, represents the adaptive threshold corresponding to the detail coefficient of the i-th layer, represents the standard deviation of the noise in the i-th layer, and N represents the number of samples of soil pore water pressure data.

[0027] Step S43: Obtain preprocessed sampling information according to the processed first information and the processed second information.

[0028] In this embodiment, Kalman filtering focuses on suppressing high-frequency vibration noise, and wavelet denoising eliminates low-frequency drift and complementarily covers the entire frequency band, significantly improving data quality and laying a solid foundation for subsequent stability analysis.

[0029] Step S5, modifying the preset double-wall steel cofferdam numerical model according to the preprocessed sampling information to obtain a modified numerical model; The step S5 also includes step S51, step S52, step S53, step S54 and step S55, which specifically include: Step S51, constructing a state vector according to the preprocessed sampling information; In this step, the state vector is defined including structural stress, water flow velocity and soil pore water pressure. The state vector is used to fully describe the state of the double-walled steel cofferdam.

[0030] Step S52, calculating an observation covariance matrix, wherein the observation covariance matrix is ​​used for correlation and variability between state vectors; In this step, the observation covariance matrix is ​​calculated, which is used to measure the correlation and variability between observations. By analyzing the relationship between sensor data, the influence of each observation on the model prediction is determined, providing a basis for the subsequent update of the state vector weight.

[0031] Step S53, updating the weight of the state vector according to the observation covariance matrix; In this step, the Kalman gain is first calculated as: ; In the above formula, represents the Kalman gain, The covariance matrix representing the prediction error of the numerical model reflects the uncertainty of the numerical model prediction; H is the observation matrix, which is used to map the model state variables to the observation space; R is the observation covariance matrix calculated based on the preprocessed sampling information collected in real time. After calculating the Kalman gain, the weight of the state vector is updated according to the update formula. The specific update formula is: ; In the above formula, is the state vector predicted by the numerical model, y is the actual observation vector, H is the observation matrix, K is the Kalman gain, and x is the updated state vector. In this way, the updated state vector is closer to the actual situation and the error of the model is reduced, so that the model's prediction of state variables such as structural stress, water flow velocity, and soil pore pressure of the double-walled steel cofferdam is more consistent with the actual measurement situation.

[0032] Step S54, using a particle swarm algorithm to determine implicit parameters and obtain corrected multi-physics field state parameters; First, the particle swarm is initialized to determine the parameters to be inverted, including the elastic modulus of soil and the residual stress of steel. The sum of squares of the errors between the structural stress, water velocity, soil pore pressure, etc. predicted by the numerical model and the actual measured values ​​is used as the measure of the fitness function. The particle swarm algorithm begins to iterate. In each iteration, the particle updates the speed and position according to its own historical optimal position and the global optimal position of the population until the preset maximum number of iterations is met, and the values ​​of implicit parameters such as the elastic modulus of soil and the residual stress of steel are obtained. In this step, the implicit parameter values ​​obtained by the particle swarm algorithm are substituted into the model, and the parameters of the model are dynamically adjusted in combination with the state vector updated by the previous ensemble Kalman filter, so as to obtain the corrected multi-physical field state parameters, including the new structural stress, water velocity, soil pore pressure, etc. These corrected parameters more accurately reflect the actual state of the double-walled steel cofferdam, provide reliable data support for subsequent analysis and decision-making, and also provide accurate information for subsequent grid adjustment, making the entire model closer to the actual situation.

[0033] The step S54 also includes step S541, step S542 and step S543, which specifically include: Step S541, obtaining the maximum and minimum values ​​of the inertia weight; Step S542, optimizing the inertia weight according to the maximum value of the inertia weight and the minimum value of the inertia weight to obtain an optimized inertia weight; Step S543: iteratively update the particle position according to the optimized inertia weight to obtain the optimal particle position and determine the implicit parameters.

[0034] In this embodiment, the optimized inertia weight is specifically: ; In the above formula, and They represent the minimum and maximum values ​​of the inertia weight, respectively, and are used to limit the value range of the inertia weight and provide boundary conditions for the algorithm's search; Represents the fitness value of the i-th particle in the current iteration; Indicates the average fitness value of particles in the current population; Indicates the optimal fitness value of the particles in the current population, and dynamically adjusts the inertia weight according to the particle fitness value. In the prediction of the stability of the double-walled steel cofferdam, when the difference between the particle fitness value and the optimal fitness value is large, the inertia weight is large. This allows the particles to jump out of the current local area and search in a larger space to avoid falling into the local optimal solution, thereby making it more likely to find the global optimal model parameter combination and improve the accuracy of the prediction of the stability of the double-walled steel cofferdam. When considering the various complex factors that affect the stability of the double-walled steel cofferdam, more reasonable parameters can be searched. At the same time, when the particle approaches the optimal solution area and the difference between the fitness value and the optimal fitness value becomes smaller, in the double-walled steel cofferdam model parameter correction, the particle can search locally and fine-tune the parameters to better fit the actual situation, thereby improving the accuracy of the model's prediction of the stability of the double-walled steel cofferdam and accurately reflecting its stability state.

[0035] Step S55, adjusting the grid resolution of the preset double-wall steel cofferdam numerical model according to the corrected multi-physical field state parameters to obtain a corrected numerical model.

[0036] In this step, according to the corrected multi-physics field state parameters, high-gradient areas that need to be meshed are identified in the structural field and soil field respectively. In the structural field, the stress concentration areas are focused on, such as welds, support nodes and other parts. These areas often experience stress concentration due to the sudden change of the structural shape or the complexity of the force. The severity of the stress change is quantified by calculating the stress gradient. The larger the stress gradient, the faster the stress change in the area, and the more fine mesh is needed to accurately capture the stress distribution. For the soil field, when the shear strain rate exceeds the shear strain rate threshold, it indicates that the deformation of the soil in this area is more severe, and a finer mesh is needed to describe its mechanical behavior. After identifying the high-gradient area, the h-adaptive method is used for local mesh encryption, and the mesh size is refined to 1 / 4 of the original size to improve the resolution of the mesh, thereby improving the calculation accuracy of the area and more accurately simulating the mechanical response of the structure and soil in these areas.

[0037] After adjusting the grid resolution, a sample set containing more than 1,000 working conditions is generated, covering different load combinations and boundary conditions, simulating various situations that may be encountered by double-walled steel cofferdams. Then, the convolutional autoencoder is used to process the sample set, map high-dimensional data to low-dimensional space, extract low-dimensional features with potential space dimensions not exceeding 100, and construct a reduced-order model. The reduced-order model is used to predict stress fields, displacement fields, and seepage fields online; the online prediction of stress fields, displacement fields, and seepage fields by the reduced-order model is compared with the real-time collected values ​​of the sensor to calculate the error between the two. In this way, the accuracy of the model prediction is verified in real time to determine whether the model is reliable. When the model is determined to be reliable, the corrected numerical model is obtained. It should be noted that in terms of fluid-solid coupling, the immersed boundary method is used to deal with the interaction between water flow and structure, accurately simulating the force of water flow on the double-walled steel cofferdam structure and the response of the structure under the action of water flow. In terms of solid-soil coupling, the contact algorithm is used to simulate the force transmission at the interface between the cofferdam and the foundation, considering the support and constraint of the soil on the cofferdam.

[0038] Step S6: predicting the stability level of the double-walled steel cofferdam structure according to the modified numerical model to obtain a prediction result.

[0039] The step S6 also includes step S61, step S62, step S63, step S64 and step S65, which specifically include: Step S61, acquiring physical field response data according to the modified numerical model; Step S62, calculating a deterministic safety factor according to the physical field response data; In this step, the deterministic safety factor includes the anti-overturning safety factor, the anti-slip safety factor, and the seepage stability factor. The specific calculation process of the anti-overturning safety factor is: ; In the above formula, W represents the deadweight of the double-walled steel cofferdam structure. It represents the horizontal distance from the structure's deadweight line to the tipping point. represents the base friction, represents the horizontal distance from the line of action of the base friction force to the overturning point, and Represent water pressure and soil pressure respectively, and H represents the vertical distance from the water pressure action point to the bottom of the double-walled steel cofferdam structure.

[0040] The specific calculation process of anti-slip safety factor is: ; In the above formula, represents the anti-slip safety factor, c represents the soil cohesion, N represents the vertical resultant force, and T represents the horizontal load.

[0041] The specific calculation process of the seepage stability coefficient is: ; In the above formula, represents the seepage stability coefficient, and represent the actual hydraulic gradient and critical hydraulic gradient respectively.

[0042] Step S63, generating a disturbance sample set using Latin hypercube sampling method; In actual engineering, there are uncertainties in environmental loads (such as wave height obeying Weibull distribution, earthquake peak acceleration following GR law), material parameters (soil elastic modulus normal distribution with coefficient of variation ±20%, weld strength Weibull distribution), and geometric errors (cofferdam installation deviation uniformly distributed ±50mm). These uncertainties will affect the stability of engineering structures. 1,000 sets of parameter combinations are generated through Latin hypercube sampling. These combinations cover the parameter space with the lowest possible deviation to comprehensively evaluate the performance of the model under uncertainties.

[0043] Step S64, calculating the failure probability according to the disturbance sample set; The step S64 also includes step S641, step S642, step S643, step S644 and step S645, which specifically include: Step S641, calculating the anti-overturning safety factor and the anti-slip safety factor corresponding to each disturbance sample in the disturbance sample set; Step S642, obtaining first threshold information and second threshold information; Step S643, judging whether the anti-overturning safety factor corresponding to each disturbance sample is less than the first threshold information, and obtaining a first judgment result; Step S644, determining whether the anti-slip safety factor corresponding to each disturbance sample is less than the second threshold information, and obtaining a second determination result; Step S645: Calculate the failure probability according to the first judgment result and the second judgment result.

[0044] In this step, the disturbance samples whose anti-overturning safety factor is less than the first threshold information or the disturbance samples whose anti-slip safety factor is less than the second threshold information are taken as failure samples. The specific calculation process of failure probability is: ; In the above formula, represents the failure probability, It indicates the number of disturbance samples whose anti-overturning safety factor is less than the first threshold information or the number of disturbance samples whose anti-slip safety factor is less than the second threshold information. One disturbance sample corresponds to two safety factors, and both of them need to be greater than the threshold information to not be considered as a failure sample. Any safety factor less than the threshold information is calculated as a failure sample.

[0045] Step S65: predicting the stability level of the double-walled steel cofferdam structure according to the deterministic safety factor and the failure probability.

[0046] In this step, the stability level of the double-walled steel cofferdam structure is predicted as follows: ; In the above formula, R is the comprehensive risk value; , as well as is the weight coefficient, which is calibrated through expert experience and historical accident data; and is the actual calculated safety factor against overturning and safety factor against sliding; and It is the preset standard value of the safety factor against overturning and the preset standard value of the safety factor against sliding; , , , All are adjusted indices, among which, It is used to control the nonlinear relationship between the deviation of the anti-overturning safety factor from the standard value and the comprehensive risk value. It is used to adjust the influence of the degree of deviation of the anti-slip safety factor from the standard value on the comprehensive risk value. Used to reflect the sensitivity of the project to the risk of probabilistic failure. It is used to control the influence of the ratio of seepage gradient to critical seepage gradient on the comprehensive risk value; represents the failure probability; represents the seepage stability coefficient; , They represent the time attenuation coefficients corresponding to the safety factors of anti-overturning and anti-slipping, and the failure probability, respectively, and are determined according to the aging characteristics of engineering materials, environmental erosion conditions, etc. In a specific implementation, when the comprehensive risk value is less than 0.3, it is a normal level; when the comprehensive risk value is greater than or equal to 0.3 and less than 0.6, it is a warning level; when the comprehensive risk value is greater than or equal to 0.6, it is an emergency level. A hierarchical control strategy is generated according to the prediction results of the stability level (normal / warning / emergency): when the prediction result of the stability level is a warning, the sampling frequency of the sensor in the abnormal area is increased from 1Hz to 50Hz, focusing on data collection; at the same time, the model is reviewed based on the re-collected data, and then the risk location image and recommended measures are pushed to the engineer; when the prediction result of the stability level is an emergency, the position and volume of the cabin to be filled with water are calculated based on the buoyancy balance equation to obtain the calculation result; a control instruction is issued based on the calculation result, and the control instruction is used to adjust the opening of the solenoid valve to control the amount of water injection.

[0047] It should be noted that the specific calculation process of the calculation results is: ; In the above formula, Indicates the calculation result, is the density of water, Indicates the magnitude of the force corresponding to the additional moment required to balance the overturning moment, ,in, The overturning moment represents the difference between the overturning moment borne by the current structure and the allowable overturning moment. represents the acceleration due to gravity, Indicates the length of the lever arm.

[0048] The present invention formulates differentiated control strategies for different risk levels. When it is at the warning level (0.3≤R<0.6), by increasing the sensor sampling frequency, triggering model recalculation and manual confirmation, it can more accurately capture abnormal data in the risk budding stage, deeply analyze risk trends, avoid misjudgment or missed judgment, and make risk response preparations in advance. After entering the emergency level (R≥0.6), the counterweight decision is immediately initiated to quickly and accurately intervene in high-risk conditions to maximize the safety of the engineering structure.

[0049] The present invention combines the deterministic safety factor and the failure probability to quantify the risk value, making full use of these rich data resources so that risk quantification is no longer limited to a single data type or analysis method, greatly improving the accuracy of risk quantification. The deterministic safety factor and the probabilistic failure risk reflect structural risks from different angles. When the deterministic safety factor is close to the threshold but has not reached it, the probabilistic failure risk may show a higher probability of failure through a large number of sample simulations, and vice versa. The fusion of the two allows the two types of information to verify and complement each other, more accurately determine the actual risk level, and effectively improve the stability prediction accuracy of the double-walled steel cofferdam structure in complex environments.

[0050] Embodiment 2: like Figure 2 As shown, this embodiment provides an intelligent prediction system for the stability of a double-walled steel cofferdam structure, the system comprising an acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904, a fourth processing module 905 and a prediction module 906, which specifically include: An acquisition module 901 is used to acquire the installation position of the sensor; A first processing module 902 is used to arrange the sensor cluster according to the installation position of the sensor; The second processing module 903 is used to collect data according to the sensor cluster to obtain sampling information, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data and soil pore water pressure data; A third processing module 904 is used to preprocess the sampling information to obtain preprocessed sampling information; The fourth processing module 905 is used to modify the preset double-wall steel cofferdam numerical model according to the pre-processed sampling information to obtain a modified numerical model; The prediction module 906 is used to predict the stability level of the double-walled steel cofferdam structure according to the modified numerical model to obtain a prediction result.

[0051] In a specific implementation of the present disclosure, the acquisition module further includes an acquisition unit, a first processing unit and a second processing unit, which specifically include: Acquisition unit, used to obtain dynamic load model and structural information of double-walled steel cofferdam; A first processing unit is used to determine the load of water flow on different parts of the double-walled steel cofferdam according to the dynamic load model; The second processing unit is used to determine the installation position of the sensor according to the load of the water flow on different parts of the double-walled steel cofferdam and the structural information of the double-walled steel cofferdam.

[0052] In a specific embodiment of the present disclosure, the third processing module further includes a third processing unit, a fourth processing unit and a fifth processing unit, which specifically include: A third processing unit is used to process the water flow velocity data included in the sampling information by using a Kalman filter to obtain processed first information; A fourth processing unit is used to process the soil pore water pressure data included in the sampling information by using a wavelet threshold denoising method to obtain processed second information; The fifth processing unit is used to obtain pre-processed sampling information according to the processed first information and the processed second information.

[0053] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0054] Embodiment 3: Corresponding to the above method embodiment, this embodiment also provides an intelligent prediction device for the stability of a double-walled steel cofferdam structure. The intelligent prediction device for the stability of a double-walled steel cofferdam structure described below and the intelligent prediction method for the stability of a double-walled steel cofferdam structure described above can be referenced to each other.

[0055] Figure 3 FIG. 8 is a block diagram of an intelligent prediction device 800 for the stability of a double-walled steel cofferdam structure according to an exemplary embodiment. Figure 3 As shown, the double-wall steel cofferdam structure stability intelligent prediction device 800 may include: a processor 801, a memory 802. The double-wall steel cofferdam structure stability intelligent prediction device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0056] The processor 801 is used to control the overall operation of the double-walled steel cofferdam structure stability intelligent prediction device 800 to complete all or part of the steps in the above-mentioned double-walled steel cofferdam structure stability intelligent prediction method. The memory 802 is used to store various types of data to support the operation of the double-walled steel cofferdam structure stability intelligent prediction device 800, which may include, for example, instructions for any application or method operating on the double-walled steel cofferdam structure stability intelligent prediction device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the double-walled steel cofferdam structure stability intelligent prediction device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0057] In an exemplary embodiment, the double-wall steel cofferdam structure stability intelligent prediction device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned double-wall steel cofferdam structure stability intelligent prediction method.

[0058] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned double-walled steel cofferdam structure stability intelligent prediction method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the double-walled steel cofferdam structure stability intelligent prediction device 800 to complete the above-mentioned double-walled steel cofferdam structure stability intelligent prediction method.

[0059] Embodiment 4: Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the intelligent prediction method for the stability of a double-walled steel cofferdam structure described above can refer to each other.

[0060] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the intelligent prediction method for the stability of a double-walled steel cofferdam structure of the above method embodiment.

[0061] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0063] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent prediction method for the stability of a double-walled steel cofferdam structure, characterized in that: include: Get the installation location of the sensor; Arranging sensor clusters according to installation locations of the sensors; According to the data collected by the sensor cluster, sampling information is obtained, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data, and soil pore water pressure data; Preprocessing the sampling information to obtain preprocessed sampling information; The preset double-wall steel cofferdam numerical model is modified according to the preprocessed sampling information to obtain a modified numerical model; The stability grade of the double-wall steel cofferdam structure is predicted based on the modified numerical model to obtain a prediction result.

2. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 1 is characterized in that: Get the installation location of the sensor, including: Obtain dynamic load models and structural information of double-walled steel cofferdams; Determine the load of water flow on different parts of the double-walled steel cofferdam according to the dynamic load model; The installation position of the sensor is determined according to the load of the water flow on different parts of the double-walled steel cofferdam and the structural information of the double-walled steel cofferdam.

3. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 1 is characterized in that: Preprocessing the sampling information to obtain preprocessed sampling information includes: Using Kalman filtering to process the water flow velocity data included in the sampling information to obtain processed first information; The soil pore water pressure data included in the sampling information is processed by using a wavelet threshold denoising method to obtain processed second information; Preprocessed sampling information is obtained according to the processed first information and the processed second information.

4. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 1 is characterized in that: The preset double-wall steel cofferdam numerical model is modified according to the preprocessed sampling information, including: Constructing a state vector according to the preprocessed sampling information; calculating an observation covariance matrix for correlation and variability between state vectors; Updating the weight of the state vector according to the observation covariance matrix; The implicit parameters are determined by using the particle swarm algorithm to obtain the corrected multi-physics field state parameters; The grid resolution of the preset double-wall steel cofferdam numerical model is adjusted according to the modified multi-physical field state parameters to obtain a modified numerical model.

5. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 4 is characterized in that: The particle swarm algorithm is used to determine the implicit parameters, including: Get the maximum and minimum values ​​of inertia weight; The inertia weight is optimized according to the maximum value of the inertia weight and the minimum value of the inertia weight to obtain the optimized inertia weight; The particle position is iteratively updated according to the optimized inertia weight to obtain the optimal particle position and determine the implicit parameters.

6. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 1 is characterized in that: The stability level of the double-walled steel cofferdam structure is predicted based on the modified numerical model, including: Acquiring physical field response data according to the modified numerical model; Calculating a deterministic safety factor based on the physical field response data; Use Latin hypercube sampling to generate a set of perturbation samples; Calculating the failure probability according to the disturbance sample set; The stability level of the double-walled steel cofferdam structure is predicted based on the deterministic safety factor and the failure probability.

7. The intelligent prediction method for the stability of double-walled steel cofferdam structure according to claim 6 is characterized in that: Calculating a deterministic safety factor based on the physical field response data includes: The anti-overturning safety factor included in the deterministic safety factor calculated according to the physical field response data is specifically: ； In the above formula, W represents the deadweight of the double-walled steel cofferdam structure. It represents the horizontal distance from the structure's deadweight line to the tipping point. represents the base friction, represents the horizontal distance from the line of action of the base friction force to the overturning point, and Represent water pressure and soil pressure respectively, and H represents the vertical distance from the water pressure action point to the bottom of the double-walled steel cofferdam structure.

8. An intelligent prediction system for the stability of double-walled steel cofferdam structures, characterized in that: include: An acquisition module, used to acquire the installation position of the sensor; A first processing module, configured to arrange a sensor cluster according to an installation position of the sensor; A second processing module is used to collect data according to the sensor cluster to obtain sampling information, wherein the sampling information includes strain data of the double-walled steel cofferdam structure, water flow velocity data, and soil pore water pressure data; A third processing module is used to preprocess the sampling information to obtain preprocessed sampling information; A fourth processing module is used to modify the preset double-wall steel cofferdam numerical model according to the preprocessed sampling information to obtain a modified numerical model; The prediction module is used to predict the stability level of the double-wall steel cofferdam structure according to the modified numerical model to obtain a prediction result.

9. The double-walled steel cofferdam structure stability intelligent prediction system according to claim 8 is characterized in that: The acquisition module comprises: Acquisition unit, used to obtain dynamic load model and structural information of double-walled steel cofferdam; A first processing unit is used to determine the load of water flow on different parts of the double-walled steel cofferdam according to the dynamic load model; The second processing unit is used to determine the installation position of the sensor according to the load of the water flow on different parts of the double-walled steel cofferdam and the structural information of the double-walled steel cofferdam.

10. The double-wall steel cofferdam structure stability intelligent prediction system according to claim 8, characterized in that: The third processing module comprises: A third processing unit is used to process the water flow velocity data included in the sampling information by using a Kalman filter to obtain processed first information; A fourth processing unit is used to process the soil pore water pressure data included in the sampling information by using a wavelet threshold denoising method to obtain processed second information; The fifth processing unit is used to obtain pre-processed sampling information according to the processed first information and the processed second information.

Images