A wharf wave impact resistant intelligent adjustment method and system

Abstract

The application relates to the technical field of wharf anti-seismic control, and discloses a wharf anti-wave impact intelligent adjustment method and system; through integration of an intelligent wave energy dissipation system, the damping characteristics and the stiffness distribution can be dynamically adjusted according to the real-time monitored wave parameters, the wave impact load is effectively reduced, the wave resistance and the structural stability of a temporary wharf in a complex and changeable water environment are improved, and the risk of structural damage caused by wave impact is reduced; the passive wave resistance is changed into active and intelligent adaptive adjustment, the wave impact can be predicted, the measures can be prepared in advance, the structural characteristics can be adjusted in real time, the adjustment scheme can be optimized after the event, the safety of the wharf in an extreme water condition and the reliability of long-term use are significantly improved; through data storage and analysis in the whole life cycle, a long-term maintenance plan and a performance evaluation report can be generated, the service life of the wharf can be prolonged, the maintenance cost can be reduced, and the operation efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of seismic control technology for wharves, specifically to an intelligent adjustment method and system for wharf resistance to wave impact. Background Technology

[0002] Temporary wharves play an irreplaceable role in temporary material transportation. Their design must cope with complex and ever-changing aquatic environments to ensure structural stability and operational safety. However, wave impact, as a major factor affecting the stability of temporary wharves, places extremely high demands on structural design. How to maintain the wave-resistant performance of the wharf structure in a dynamic wave environment, while also considering ease of construction and user comfort, is a key problem that urgently needs to be solved in this field.

[0003] Existing technologies for dealing with wave impacts often rely on rigid designs of fixed structures or simple wave-damping devices. These methods are difficult to adapt flexibly to different water conditions when faced with complex and variable wave conditions. The impact load of waves on temporary wharf structures is highly dynamic and random, which makes designing an energy-dissipating system that can respond to wave changes in real time a core technical challenge.

[0004] The primary challenge lies in achieving dynamic adaptability of the structure, that is, automatically adjusting the damping and stiffness characteristics of the structure under different wave intensities and frequencies to effectively reduce impact loads. Achieving dynamic adaptability relies on accurate real-time monitoring of wave parameters, but existing monitoring technologies often struggle to accurately capture subtle differences in water flow velocity and pressure changes in complex environments.

[0005] This leads to another key issue: how to achieve rapid response of damping devices through intelligent control based on dynamic monitoring, so as to optimize the structure's dissipation of wave energy.

[0006] Therefore, the key issue of this study is how to integrate an intelligent wave energy dissipation system into a temporary wharf structure, enabling it to dynamically adjust damping characteristics and stiffness distribution based on real-time monitored wave parameters, thereby effectively reducing wave impact loads and improving structural stability.

[0007] When strong winds and waves strike, if the wharf structure cannot quickly adjust its own characteristics to allow some water to pass through and reduce resistance, the pile foundation connection may be damaged due to excessive stress. In calm conditions, if the structure cannot enhance its overall rigidity in time, it may affect the comfort of use and the load-bearing capacity.

[0008] The solution to this problem will directly affect the safety and practicality of temporary docks in variable environments.

[0009] By focusing on the two major technical challenges of dynamic adaptability and intelligent control, this study aims to reveal the shortcomings of existing temporary wharf designs in dealing with complex wave environments and to provide a clear technical direction for developing more efficient and flexible wave energy dissipation systems.

[0010] The ultimate goal is to improve the temporary pier's wave resistance under extreme water conditions and its long-term reliability. Summary of the Invention

[0011] The purpose of this invention is to provide an intelligent adjustment method and system for resisting wave impact at wharves, so as to solve the problems mentioned in the background art.

[0012] To achieve the above objectives, the present invention provides the following technical solution: an intelligent adjustment method and system for resisting wave impact at a wharf, comprising the following steps:

[0013] S1. Obtain environmental dynamic parameters from the aquatic environment through a sensor array. The environmental dynamic parameters include wave height, wave frequency, and wave speed. Process the parameters to obtain parameter classification results. S2. Determine the dynamic intensity of the environment based on the parameter classification results. If the dynamic intensity of the environment exceeds the preset intensity threshold, activate the prediction module to simulate the future dynamic change trend of the environment and determine the peak distribution of the impact load. S3. Based on the peak distribution of impact load, stress distribution analysis is performed on the stressed components. A numerical analysis model is used to calculate the matching degree between the current adjustment characteristics and stiffness distribution, and a quantitative evaluation index of optimization requirements is obtained. S4. If the quantitative evaluation index is lower than the preset optimization standard, the response time characteristics of the regulating device are judged by integrating historical environmental data and real-time dynamic environmental parameters through the information processing link, and a dynamic regulation scheme is generated. S4. Extract the target adjustment value and stiffness value from the dynamic adjustment scheme, send the adjustment command to the adjustment execution unit, and determine the deformation configuration of the stressed component.

[0014] Preferably, step S1 further includes: S11. Based on time-frequency eigenvalues, feature extraction is performed to generate feature vectors of wave parameters, and the main components of the feature vectors are determined. S12. If the main components of the feature vector exceed the preset threshold, the feature vector is classified by the support vector machine algorithm to obtain the classification result of the wave parameters. S13. Use data fusion methods to integrate the classification results of multiple sensor arrays, generate comprehensive environmental dynamic parameter classification results, and determine the intensity of water environment fluctuations.

[0015] Preferably, the time-frequency characteristic values ​​in step S11 include the peak frequency, average amplitude, and velocity distribution of the wave height; the preset threshold in step S12 is determined according to the characteristics of the aquatic environment.

[0016] Preferably, step S2 further includes: S21. Based on time series analysis algorithms and historical data, simulate the dynamic changes in the environment to obtain trend prediction results; S22. Calculate the peak distribution prediction based on the trend prediction results to determine the peak distribution of the impact load.

[0017] Preferably, the time series analysis in step S21 uses an autoregressive model to predict wave dynamics over a future period based on the patterns of historical wave data. The autoregressive model analyzes the time series of wave height, frequency, and velocity to determine the autocorrelation of the data and generate trend predictions for the next few minutes or hours. In step S22, the peak distribution of impact load reflects the maximum force exerted by waves on the stressed components. The calculation process is based on the predicted wave height and velocity, combined with a physical model to determine the magnitude and distribution of the impact force.

[0018] Preferably, step S3 further includes: S31. If there are local stress concentration areas in the first stress distribution data, the optimized second stress distribution data can be obtained by adjusting the mesh density and material parameters and recalculating using a numerical analysis model. S32, Based on the second stress distribution data, a dynamic simulation tool is used to simulate the adjustment characteristics of the component. By comparing the simulation results with the preset performance threshold, the stiffness distribution parameters of the component are determined. S33 uses a genetic algorithm to adjust the parameters of the component based on the stiffness distribution parameters, obtains quantitative evaluation indicators, and determines whether the optimization requirements meet the preset performance requirements.

[0019] Preferably, the local stress concentration area in step S31 is identified by abnormally high stress values; in step S32, the dynamic simulation tool evaluates the deformation and stiffness characteristics of the component by simulating the dynamic response of the component under impact load; and in step S33, the genetic algorithm optimizes the stiffness distribution parameters of the component by simulating the natural selection process.

[0020] Preferably, step S4 further includes: S41. Use database query tools to extract historical environmental data, and use stream processing tools to process real-time dynamic environmental parameters to obtain a comprehensive environmental dataset. S42. If the quantitative evaluation index of the comprehensive environmental dataset is lower than the preset optimization standard, the comprehensive environmental dataset is analyzed through the information processing link to determine the response time characteristics of the regulating device. S43. Use the decision tree algorithm to classify the comprehensive environmental dataset and determine the response time characteristics; S44. Generate a dynamic adjustment scheme based on the response time characteristics, and convert the dynamic adjustment scheme into control commands using a control command generation tool; S45. Use the rule engine to generate a dynamic adjustment scheme based on the response time characteristics to obtain control instructions; S46. Execute control commands through the adjustment device to adjust environmental parameters to meet preset optimization standards; S47. Use automated control tools to send control commands to the regulating device to complete the adjustment of environmental parameters; The database query tool in step S41 extracts historical wave data from a preset database, including time series of wave height, frequency, and speed. The information processing step in step S42 analyzes the comprehensive environmental dataset to evaluate the response speed and effectiveness of the control device in the current environment. The decision tree algorithm in step S43 generates classification rules based on the characteristics of the comprehensive environmental dataset, such as wave height, frequency, and response time requirements. The dynamic adjustment scheme in step S44 is based on response time characteristics to determine the specific actions of the adjustment device, such as adjusting the angle of the servo motor or the pressure of the hydraulic system. The rule engine in step S45 generates an adjustment scheme based on a preset rule base and combined with response time characteristics. The rule base contains a mapping relationship between various environmental conditions and adjustment actions. The adjustment device in step S46 includes a servo motor, a hydraulic system, or a robotic arm, and performs specific adjustment actions according to control commands. In step S47, the automation control tool transmits instructions to the regulating device through an industrial control protocol.

[0021] Preferably, step S5 further includes: S51. According to the parameter set, if the target adjustment value exceeds the preset threshold, the adjustment range is calculated by combining the stiffness value with the logic judgment module, an adjustment command is generated, stored in the command queue, and the generated adjustment command set is determined. S52. Obtain the adjustment instruction set through the adjustment execution unit, call the control interface to send the adjustment instructions to the stressed component, complete the instruction execution, and obtain the response status of the stressed component; S53. Based on the response status, the deformation parameters of the stressed component are analyzed by combining the stiffness value with the physical mapping module, stored in the deformation database, and the final deformation configuration is determined. S54. Based on the final deformation configuration, generate optimized design suggestions for the stressed components and store them in the design database; S55. Regularly update the deformation database and design database, and optimize the generation logic of dynamic adjustment schemes by combining real-time environmental data and historical data. S56. Based on the optimized dynamic adjustment scheme, generate a long-term maintenance plan to guide the periodic inspection and performance evaluation of load-bearing components; S57. Combine the dynamic adjustment scheme and maintenance plan to generate a performance evaluation report for the component and store it in the evaluation database; S58. Based on the performance evaluation report, optimize the deployment strategy of the sensor array to improve the accuracy and coverage of data acquisition; S59. Based on the optimized sensor array, periodically verify the execution effect of the dynamic adjustment scheme and update the adjustment logic to adapt to long-term environmental changes. S510, combining the optimized adjustment logic and maintenance plan, generates a dynamic performance monitoring scheme for the component, and tracks the operating status of the component in real time.

[0022] The present invention also provides an intelligent adjustment system for piers to resist wave impact, comprising: The perception layer includes an environmental perception and data processing module. This module acquires raw wave height, wave frequency, and wave speed signals in real time through sensor arrays deployed at key locations on buoys and wharf structures. It then performs noise reduction and filtering on the raw signals, and uses Fourier transform for time-frequency analysis to extract the wave's time-frequency characteristics. Principal component analysis is used for dimensionality reduction to extract core feature vectors, and algorithms such as support vector machines are used to classify the wave state. Finally, the classification results from multiple sensors are integrated to generate environmental dynamic parameter classification results, accurately determining the current wave state of the water area. The cognitive and decision-making layer includes a wave prediction and load analysis module, a structural health diagnosis and assessment module, and an intelligent decision-making and solution generation module. The wave prediction and load analysis module can predict future wave trends and their impact on the wharf based on current and historical data. The structural health diagnosis and assessment module is used to assess the health status of the wharf structure under current and predicted loads. The intelligent decision-making and solution generation module is used to formulate the optimal adjustment strategy based on the diagnostic results. The execution layer includes an instruction execution and dynamic adjustment module, which is used to put decisions into practice. The optimization and evolution layer includes a performance monitoring and system optimization module, which is used to compare the adjustment target with the actual effect and verify the effectiveness of the dynamic adjustment scheme.

[0023] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention integrates an intelligent wave energy dissipation system, which can dynamically adjust damping characteristics and stiffness distribution based on real-time monitored wave parameters. This effectively reduces wave impact loads, enhances the wave resistance and structural stability of temporary wharves in complex and variable aquatic environments, and reduces the risk of structural damage caused by wave impacts.

[0024] This invention transforms passive wave resistance into active, intelligent adaptive adjustment, enabling it to predict wave impacts, prepare countermeasures in advance, adjust structural characteristics in real time, and optimize adjustment schemes afterward, forming a complete intelligent operation and maintenance closed loop, which significantly improves the safety of the wharf under extreme water conditions and the reliability of its long-term use.

[0025] This invention, through the storage and analysis of data throughout the entire lifecycle, can generate long-term maintenance plans and performance evaluation reports, providing data support for preventive maintenance and design improvements at the terminal, helping to extend the terminal's service life, reduce maintenance costs, and improve operational efficiency. Attached Figure Description

[0026] Fig. 1 A flowchart illustrating a preferred embodiment of the intelligent adjustment method for resisting wave impact at a wharf provided by the present invention; Fig. 2 A system framework diagram of the intelligent adjustment system for wharf wave impact resistance provided by the present invention; Detailed Implementation The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Please see Figs. 1-2 As shown, a smart adjustment method for resisting wave impact at a wharf is described in detail below with reference to specific implementation methods.

[0028] Step S1 involves acquiring dynamic environmental parameters from the aquatic environment using a sensor array. These parameters include wave height, wave frequency, and wave velocity, and processing them to obtain parameter classification results. For example, the aquatic environment can be an ocean, lake, or river. The sensor array is typically deployed at multiple key locations within the waterway, such as buoys, fixed monitoring stations, or vessels. The sensor array includes various types of sensors, such as ultrasonic rangefinders, accelerometers, and current meters, to capture raw signals of wave height, frequency, and velocity, respectively. These sensors acquire continuous wave dynamic data through high-frequency sampling, ensuring the real-time nature and accuracy of the data. It should be noted that the deployment of the sensor array must consider the complexity of the aquatic environment. For example, in nearshore areas, waves may exhibit non-linear variations due to topographical influences; therefore, the sensors need to be evenly distributed to cover different areas.

[0029] Specifically, the acquired raw signals are time-series data, typically output in the form of voltage or current, reflecting the physical characteristics of the waves. The sensor array converts these signals into digital signals using an analog-to-digital converter before transmitting them to the data processing unit. In one possible implementation, the data processing unit first preprocesses the raw signals, including denoising and filtering operations, to eliminate environmental interference, such as wind noise or the effects of water turbulence.

[0030] A low-pass filter can be used to remove high-frequency noise and ensure signal smoothness. Subsequently, a Fourier transform is performed on the preprocessed signal to conduct time-frequency analysis and extract the time-frequency features of the wave signal. These features include the wave's frequency components, amplitude distribution, and phase information, characterizing the dynamic changes of the waves. The Fourier transform decomposes the time-domain signal into sinusoidal components of different frequencies, generating a spectrum for subsequent feature extraction.

[0031] Step S11 involves feature extraction based on time-frequency feature values ​​to generate feature vectors for wave parameters and determine the principal components of the feature vectors. In one embodiment, the time-frequency feature values ​​contain data across multiple dimensions, such as the peak frequency of wave height, average amplitude, and velocity distribution. Principal component analysis (PCA) is a dimensionality reduction method used to extract key information from high-dimensional time-frequency feature values.

[0032] Specifically, Principal Component Analysis (PCA) determines the principal component directions of the data—that is, the directions with the largest variance—by calculating the covariance matrix of the eigenvalues. These principal components typically reflect the main trends in wave dynamics, such as rapid changes in high-frequency waves or persistent fluctuations in low-frequency waves. The output of PCA is a low-dimensional eigenvector, usually containing 2 to 5 principal components, with the specific dimensions depending on the data complexity and analytical requirements.

[0033] In marine environments, waves may exhibit multiple superimposed frequencies. Principal component analysis (PCA) can effectively separate the dominant frequency components, reducing redundant information. It should be noted that the principal components of the eigenvectors are determined through eigenvalue decomposition; the components with larger eigenvalues ​​correspond to the main characteristics of wave dynamics.

[0034] In nearshore areas, periodic variations in wave height may account for the majority of the variance, while in deep-sea areas, the distribution of wave velocity may be more significant. Principal component analysis (PCA) can be implemented using linear algebra libraries, for example, by calculating eigenvectors and eigenvalues ​​through matrix factorization. The generated eigenvectors not only retain the key information of the original signal but also reduce the computational complexity of subsequent processing.

[0035] Step S12: If the main component of the feature vector exceeds the preset threshold, the feature vector is classified by the support vector machine algorithm to obtain the classification result of the wave parameters.

[0036] Specifically, the preset threshold is determined based on the characteristics of the aquatic environment. For example, in storm-prone sea areas, the threshold may be higher to filter out significant wave dynamics, while in calm lake environments, the threshold may be lower to capture subtle fluctuations. The Support Vector Machine (SVM) algorithm constructs a hyperplane to classify feature vectors into different categories, such as "high-intensity waves," "medium-intensity waves," and "low-intensity waves." The classification process is based on the principal components of the feature vectors; for example, waves with a principal component height exceeding 1 meter or a frequency exceeding 0.5 Hz may be classified as high-intensity waves. In one possible implementation, the SVM uses kernel functions (such as radial basis functions) to handle non-linearly separable feature vectors. The kernel function maps low-dimensional features to a high-dimensional space, making the originally complex classification boundaries linearly separable.

[0037] In an embodiment located in a nearshore area, the feature vectors of wave height and frequency may exhibit a non-linear distribution. A support vector machine (SVM) uses a kernel function to find the optimal classification boundary, accurately distinguishing different wave states. The classification results are output as category labels, such as a value of 1 for "high-intensity wave" and a value of 0 for "low-intensity wave". It should be noted that the SVM is trained based on historical wave data, and the training set includes wave feature vectors and corresponding wave state labels under various environmental conditions to ensure the model's generalization ability.

[0038] Step S13: A data fusion method is used to integrate the classification results of the multi-sensor array, generating a comprehensive classification result of environmental dynamic parameters to determine the wave state of the aquatic environment. For example, the classification results of the multi-sensor array may differ; for instance, sensors at different locations may output different wave intensity categories due to terrain or water flow influences. The data fusion method integrates these results through weighted averaging, voting mechanisms, or Bayesian inference to generate a unified classification result.

[0039] Specifically, the weighted average method assigns weights based on the reliability of the sensor locations; for example, sensors near deep water may have higher weights because their data better reflects overall wave dynamics. The fused classification result is output as a probability, such as "80% probability of high-intensity wave". In one embodiment, data fusion employs a majority voting mechanism, whereby when multiple sensor classifications point to the same category, that category is selected as the final result.

[0040] Assuming five sensors are deployed, with three outputting "high-intensity fluctuations" and two outputting "moderate-intensity fluctuations," the fusion result will be "high-intensity fluctuations." It's important to note that the fusion process must also consider the time synchronization of the sensors to ensure all data corresponds to the same time window. The fused comprehensive classification result is used to determine the fluctuation state of the aquatic environment. High-intensity fluctuations may trigger subsequent prediction modules, while low-intensity fluctuations may only require data recording. This judgment provides a reliable basis for subsequent dynamic adjustments.

[0041] Step S2: Determine the environmental dynamic intensity based on the parameter classification results. If the environmental dynamic intensity exceeds a preset intensity threshold, activate the prediction module to simulate future environmental dynamic changes and determine the peak distribution of the impact load. In one possible implementation, the environmental dynamic intensity is determined by the probability value or category label of the comprehensive classification results.

[0042] When the classification result is "high-intensity fluctuation" and the probability exceeds 70%, the environmental dynamic intensity is determined to exceed a preset threshold. The preset intensity threshold is set according to the application scenario of the aquatic environment. For example, in the Yangtze River project, the threshold may be determined based on the safe bearing capacity of the ship or platform. After activating the prediction module, the system enters the high-intensity fluctuation response mode and calls the time series analysis algorithm to perform trend prediction.

[0043] Specifically, the prediction module acquires real-time data from the sensor array. The data is collected at a fixed frequency (e.g., 10 times per second) and includes the latest values ​​for wave height, frequency, and velocity. The acquisition frequency of the real-time data must be matched to the sensor hardware performance. For example, in highly dynamic environments, the acquisition frequency may be increased to 50 times per second to capture rapidly changing wave characteristics. The acquired real-time data, after preprocessing, is input into a time series analysis algorithm. Time series analysis identifies the periodicity and trend of wave dynamics by comparing historical and real-time data.

[0044] The algorithm may detect that the wave height has been rising continuously over the past 10 minutes, indicating that higher intensity fluctuations may occur in the future.

[0045] Step S21: Based on time series analysis algorithms and historical data, the simulated environmental dynamics are compared to obtain trend prediction results. In one embodiment, the time series analysis uses an autoregressive model to predict wave dynamics over a future period based on the patterns in historical wave data. The autoregressive model analyzes the time series of wave height, frequency, and speed to determine the autocorrelation of the data and generate trend predictions for the next few minutes or hours.

[0046] In the Yangtze River environment, the model might predict a 20% increase in wave height and a 0.2 Hz increase in frequency within the next 30 minutes. It should be noted that the selection of historical data needs to cover various environmental conditions. For example, storms, calm periods, and transitional phases are used to improve the robustness of forecasts. In another embodiment, time series analysis is combined with moving average methods to smooth short-term fluctuations and highlight long-term trends.

[0047] In lake environments, wave dynamics can be significantly influenced by wind speed. The moving average method can effectively filter out noise caused by sudden changes in wind speed, generating stable trend predictions. The prediction results are output in time series format, including future values ​​of wave height, frequency, and velocity. These values ​​are used to subsequently calculate the peak impact load distribution.

[0048] In a nearshore scenario, the prediction results show that the wave height will reach 2 meters within the next hour, and the system enters a high-load preparation state accordingly.

[0049] Step S22: Calculate the peak distribution prediction based on the trend prediction results to determine the peak distribution of the impact load.

[0050] Specifically, the peak impact load distribution reflects the maximum force exerted by waves on stressed components (such as ship decks or fixed platforms). The calculation process is based on predicted wave height and velocity, combined with a physical model to determine the magnitude and distribution of the impact force.

[0051] At higher wave heights, the impact force may be concentrated on the wave-facing side of the structure, while at higher speeds, the impact force may exhibit periodic pulses. The peak distribution is output in the form of probability density. For example, "the maximum impact load is 500 kN, concentrated at the front end of the component." In one possible implementation, the peak distribution calculation uses the principle of energy conservation to convert the kinetic energy of the wave into an impact force on the component.

[0052] Specifically, the kinetic energy of waves is calculated based on their height and velocity, and combined with the geometric characteristics of the components (such as surface area and wave angle) to determine the distribution area of ​​the impact load.

[0053] In a scenario involving a Yangtze River platform, calculations showed that the peak impact load was mainly distributed at the bottom of the platform's support columns, and the system optimized subsequent stress analysis based on this. This calculation method ensures consistency between the predicted results and the actual physical process, providing a reliable basis for optimizing stressed components.

[0054] Step S3 involves performing stress distribution analysis on the stressed components based on the peak impact load distribution. A numerical analysis model is used to calculate the matching degree between the current adjustment characteristics and stiffness distribution, yielding a quantitative evaluation index of the optimization requirements. In one embodiment, the stressed components can be the foundation structure of a Yangtze River platform, the deck of a ship, or the panels of a breakwater. The peak impact load distribution data serves as input, reflecting the dynamic force of waves on the components. The stress distribution analysis uses a numerical analysis model to simulate the mechanical response of the components under different loads, generating stress distribution data.

[0055] The model may show stress concentration areas at the front end of the component, indicating that these areas require optimized design.

[0056] Specifically, the numerical analysis model is implemented using the finite element analysis tool. Finite element analysis calculates the stress state of each element by dividing the stressed component into multiple mesh elements. The mesh generation needs to be adjusted according to the geometric complexity of the component. For example, at component edges or connections, the mesh density is higher to capture local stress variations. Boundary conditions are set to reflect the actual action of wave loads. Examples include fixed-end constraints or dynamic load inputs. The output of the finite element analysis is the first stress distribution data, which includes the stress value and direction for each mesh element.

[0057] In a ship deck scenario, analysis showed that the stress value in the middle of the deck reached 200 MPa, exceeding the material's safety threshold, indicating a risk of stress concentration.

[0058] Step S31: If local stress concentration regions exist in the first stress distribution data, the second stress distribution data is obtained by recalculating using a numerical analysis model after adjusting the mesh density and material parameters. In one possible implementation, local stress concentration regions are identified by abnormally high stress values. For example, the stress value of a certain mesh element exceeds twice the average value. Adjusting the mesh density can improve the calculation accuracy. For example, increasing the mesh count and refining the element size in stress concentration areas. Adjusting material parameters includes changing the elastic modulus or yield strength of the component to optimize stress distribution.

[0059] In the Yangtze River platform scenario, increasing the material thickness of the support columns reduces local stress concentration, generating a second stress distribution data. In another embodiment, the optimization process combines iterative calculations; after each adjustment of mesh density or material parameters, the finite element analysis is rerun until the stress distribution meets safety requirements.

[0060] Initial analysis revealed stress concentration at the bottom of the platform support columns. After adjustment, the stress value decreased to 150 MPa, meeting design standards. The second set of stress distribution data reflected the optimized mechanical state of the component, providing a basis for subsequent stiffness distribution analysis. This iterative optimization method effectively balances computational accuracy and efficiency, ensuring the reliability of the component.

[0061] Step S32: Based on the second stress distribution data, a dynamic simulation tool is used to simulate the adjustment characteristics of the component. By comparing the simulation results with preset performance thresholds, the stiffness distribution parameters of the component are determined. For example, the dynamic simulation tool evaluates the deformation and stiffness characteristics of the component by simulating its dynamic response under impact loads. The simulation process is based on the second stress distribution data, inputting the component's geometric model and material properties to simulate the periodic action of wave loads.

[0062] In the ship deck scenario, simulations show that the maximum deformation of the deck under high-intensity waves is 5 mm, and the stiffness distribution parameters need to be adjusted to reduce the deformation.

[0063] Specifically, the dynamic simulation tool calculates the dynamic response of the component using a time-stepping method, generating deformation curves and stiffness distributions. Preset performance thresholds are determined based on the component's design requirements; for example, the maximum deformation must not exceed 3 millimeters. After comparing the simulation results with the thresholds, if the deformation exceeds the threshold, the stiffness distribution parameters are adjusted. For example, increasing the support density of a component or changing the material stiffness. The stiffness distribution parameters are output in matrix form, describing the stiffness values ​​of each region of the component.

[0064] In a breakwater scenario, the simulation display panel showed insufficient stiffness in the middle. Based on this, the system increased the number of support beams to optimize the stiffness distribution.

[0065] Step S33: Using the stiffness distribution parameters, a genetic algorithm is employed to adjust the parameters of the component, obtain quantitative evaluation indicators, and determine whether the optimization requirements meet the preset performance requirements. In one embodiment, the genetic algorithm optimizes the stiffness distribution parameters of the component by simulating the natural selection process. The algorithm uses the stiffness distribution parameters as the initial population and generates a better parameter combination through crossover, mutation, and selection operations.

[0066] In the Yangtze River platform scenario, a genetic algorithm adjusts the stiffness values ​​of the support columns to ensure stability under high-intensity waves. The optimized parameter combination generates quantitative evaluation indicators. For example, the maximum stress value of the component is reduced to 120 MPa, and the deformation is controlled within 2 mm. It should be noted that the quantitative evaluation indicators are calculated by comprehensively considering stiffness distribution, stress values, and deformation data to reflect the overall performance of the component. Preset performance requirements are set according to the application scenario. For example, in marine engineering, components are required to exhibit no plastic deformation under extreme wave conditions. If the requirements are met, the optimization process ends; otherwise, subsequent adjustment steps are initiated. This optimization method uses iterative calculations to gradually approach the optimal solution, thereby improving the adaptability of the components.

[0067] Step S4: If the quantitative evaluation index is lower than the preset optimization standard, then through the information processing stage, historical environmental data and real-time dynamic environmental parameters are integrated to determine the response time characteristics of the adjustment device and generate a dynamic adjustment scheme. In one possible implementation, a quantitative evaluation index lower than the preset optimization standard indicates that the current stiffness distribution or stress state of the component cannot fully adapt to environmental fluctuations.

[0068] In the Yangtze River platform scenario, the indicators show that the maximum stress value is still higher than the safety threshold, requiring further adjustment. The information processing stage integrates historical environmental data and real-time dynamic environmental parameters to generate a comprehensive environmental dataset, which is used to analyze the response characteristics of the control device.

[0069] Specifically, historical environmental data, including wave height, frequency, and velocity data from the past few hours or days, is stored in a database. Real-time environmental dynamic parameters are acquired in real time through a sensor array, containing the latest wave dynamic information. The fusion process uses database query tools to extract historical data and stream processing tools to process the real-time data.

[0070] In the shipboard scenario, the stream processing tool processes real-time data 10 times per second, aligns it with historical data over time, and generates a comprehensive environmental dataset. It should be noted that the dataset fusion needs to consider data weights. For example, real-time data may have a higher weight to reflect current fluctuations. In another embodiment, the fusion process uses a time-weighted average method, giving higher weight to recent data to improve the timeliness of the dataset.

[0071] In the nearshore area, the merged dataset shows a significant increase in wave frequency over the past hour, indicating an intensification of environmental dynamics.

[0072] Step S41: Historical environmental data is extracted using a database query tool, and real-time environmental dynamic parameters are processed using a stream processing tool to obtain a comprehensive environmental dataset. For example, the database query tool extracts historical wave data from a preset database, including time series data for wave height, frequency, and speed. The query process filters data based on time range and environmental conditions. For example, extracting data under storm conditions over the past 24 hours. Streaming tools perform real-time analysis of real-time data to extract the dynamic characteristics of waves. Examples include amplitude variations or frequency shifts. In one embodiment, the stream processing tool employs a sliding window mechanism to process real-time data from the most recent 10 seconds, generating short-term feature vectors. The comprehensive environmental dataset merges historical data and real-time feature vectors to form a multidimensional dataset containing both long-term trends and short-term variations in wave dynamics.

[0073] In the breakwater scenario, the dataset shows that wave height increased from 1 meter to 2 meters over the past 6 hours, and real-time data indicates a current frequency of 0.6 Hz. It should be noted that the data fusion process must ensure data consistency. For example, aligning historical and real-time data using timestamps avoids data bias. The fused dataset provides comprehensive environmental information for subsequent analysis, reflecting the complexity of wave dynamics.

[0074] Step S42: If the quantitative evaluation index of the comprehensive environmental dataset is lower than the preset optimization standard, the comprehensive environmental dataset is analyzed through the information processing link to determine the response time characteristics of the regulating device.

[0075] Specifically, the information processing stage analyzes a comprehensive environmental dataset to evaluate the response speed and effectiveness of the control device under the current environment.

[0076] In the Yangtze River platform scenario, analysis shows that the control system needs to complete parameter adjustments within 5 seconds to cope with rapidly changing wave dynamics. The response time characteristics are determined using changes in wave frequency and intensity from the dataset. For example, high-frequency waves require a faster response time. In one possible implementation, the analysis process employs statistical methods to calculate the dynamic rate of change of waves in the dataset. For example, when the frequency change exceeds 0.2 Hz per second, the regulating device must respond within 3 seconds. It should be noted that the judgment of response time characteristics also needs to consider the hardware performance of the device. For example, the response speed of a servo motor or the settling time of a hydraulic system. In another embodiment, the analysis combines machine learning methods to predict the device's response time by training a model.

[0077] In the ship scenario, the model predicts a response delay of 2 seconds for the device under high-intensity waves based on historical data, which is lower than the required 1 second, indicating that the device parameters need to be optimized. The analysis results are output in the form of response time parameters. For example, "maximum response delay 3 seconds".

[0078] Step S43: The decision tree algorithm is used to classify the comprehensive environmental dataset and determine its response time characteristics. In one embodiment, the decision tree algorithm classifies the comprehensive environmental dataset based on its characteristics. For example, wave height, frequency, and response time requirements are used to generate classification rules. These rules categorize environmental conditions into different classes. For example, "fast response", "medium response" and "slow response".

[0079] In the nearshore area, the dataset shows a high wave frequency, and the decision tree classifies the environmental state as "rapid response," requiring the control device to complete the adjustment within 2 seconds.

[0080] Specifically, decision trees generate a tree structure by recursively splitting the dataset, with each node corresponding to a feature condition. For example, "wave height greater than 1.5 meters" or "frequency greater than 0.5 Hz". The classification results are output as category labels, indicating the response time requirements of the control device. In one possible implementation, the decision tree is combined with pruning techniques to reduce the risk of overfitting and improve the generalization ability of the classification.

[0081] In the breakwater scenario, the decision tree, based on historical and real-time data, requires the prediction device to adjust within 3 seconds to cope with high-intensity waves. It should be noted that the decision tree is trained on a labeled dataset containing response time labels under various environmental conditions to ensure the model's robustness.

[0082] Step S44: Generate a dynamic adjustment scheme based on the response time characteristics, and convert the dynamic adjustment scheme into control commands using a control command generation tool. For example, the dynamic adjustment scheme determines the specific actions of the adjustment device based on the response time characteristics. For example, adjusting the angle of the servo motor or the pressure of the hydraulic system. In the Yangtze River platform scenario, the solution might require increasing the stiffness of the support columns by 20% within 2 seconds to cope with high-intensity waves.

[0083] Specifically, the control command generation tool parses the adjustment scheme into specific control signals. Examples include voltage values ​​or pulse width modulation signals. The generation process is based on a preset instruction template, ensuring signal compatibility with the hardware interface of the regulating device.

[0084] In a marine scenario, the command generation tool translates the adjustment scheme into a series of motor speed commands to control the deck's tilt angle. It should be noted that command generation must take into account the device's execution latency. For example, the start-up time of a servo motor might be 0.5 seconds, requiring a buffer time to be reserved in the design. In another embodiment, the generation tool incorporates a feedback mechanism to adjust the command parameters in real time.

[0085] In the breakwater scenario, the tool dynamically modifies instructions based on real-time feedback from the device to ensure that the adjustment effect achieves the expected result.

[0086] Step S45: The rule engine generates a dynamic adjustment scheme based on response time characteristics to obtain control instructions. In one possible implementation, the rule engine generates the adjustment scheme based on a preset rule base and the response time characteristics. The rule base contains mapping relationships between various environmental conditions and adjustment actions. For example, "If the wave height is greater than 2 meters, then increase the stiffness by 30%." In the Yangtze River platform scenario, the rule engine selects the corresponding adjustment rule based on the classification results of the decision tree and generates control instructions.

[0087] The command might require the hydraulic system to increase pressure to 500 kPa within 3 seconds. It should be noted that the rule engine supports dynamic updates, allowing rules to be adjusted based on new environmental data.

[0088] In nearshore areas, new rules require prioritizing the adjustment of the wave-facing angle of structural members under high-frequency wave conditions. Control commands are output in a standard format. For example, digital or analog signals are used to ensure compatibility with the regulating device. In another embodiment, the rule engine incorporates a priority mechanism to prioritize the execution of instructions with high response time requirements.

[0089] In a ship scenario, the rules engine prioritizes generating deck tilt adjustment commands to quickly respond to wave impacts.

[0090] Step S46: The control command is executed through the adjustment device to adjust the environmental parameters to meet the preset optimization standard. Exemplarily, the adjustment device includes a servo motor, a hydraulic system, or a robotic arm, which executes specific adjustment actions according to the control command.

[0091] In the Yangtze River platform scenario, the hydraulic system increases the pressure on the support columns according to instructions, so that the stiffness of the components can adapt to high-intensity waves.

[0092] Specifically, the execution process is implemented through a control interface, which translates instructions into physical actions of the device. For example, changing the motor speed or the opening of a hydraulic valve. In one embodiment, the process includes real-time monitoring, with the device using sensors to provide feedback on the current adjustment status. For example, stiffness values ​​or deformation data. If feedback indicates that the adjustment has not achieved the expected results, the instruction is regenerated.

[0093] In the breakwater scenario, after the device executes the command, if the sensor detects that the panel deformation still exceeds 3 mm, the system automatically adjusts the command to increase the tension of the reinforcing steel. It should be noted that the execution accuracy of the adjustment device directly affects the adjustment effect; therefore, the hardware parameters need to be calibrated periodically. For example, the response speed of an electric motor or the pressure stability of a hydraulic system.

[0094] Step S47: An automated control tool sends control commands to the regulating device to complete the adjustment of environmental parameters. In one possible implementation, the automated control tool transmits commands to the regulating device via an industrial control protocol (such as Modbus or CAN). The transmission process must ensure low latency and high reliability. For example, in marine environments, signal transmission may be subject to electromagnetic interference, requiring the use of shielded cables or redundant communication mechanisms.

[0095] In a marine setting, control tools send commands to the deck adjustment motors via the CAN bus, ensuring that the commands arrive within one second.

[0096] Specifically, the automation control tool supports multi-channel parallel transmission, allowing multiple control devices to execute commands simultaneously.

[0097] In a breakwater scenario, multiple hydraulic systems simultaneously receive commands to adjust the stiffness and wave-facing angle of the panels. It's important to note that the control tools must also support fault detection; if a command execution fails, an alarm mechanism is triggered, notifying the system to regenerate the command. After adjustment, environmental parameters (such as component stiffness or deformation) reach preset optimization standards. For example, deformation is controlled within 2 mm and stress value is below 150 MPa.

[0098] Step S5: Extract the target adjustment value and stiffness value from the dynamic adjustment scheme, send the adjustment command to the adjustment execution unit, and determine the deformation configuration of the stressed component. In one embodiment, the dynamic adjustment scheme is stored in the form of a data stream, including the target adjustment value (such as stiffness increment or angle adjustment value) and stiffness value. The data extraction module obtains these parameters by parsing the data stream and stores them in the parameter database.

[0099] In the Yangtze River platform scenario, the extraction module obtains the target stiffness increment as 20% and the stiffness value as 5000 kN / m from the scheme.

[0100] Specifically, the extraction process is based on a preset data format, such as JSON or XML, to ensure the accuracy of the parameters. The parameter database stores data in key-value pairs. For example, "Stiffness value: 5000 kN / m" and "Adjustment increment: 20%". In another embodiment, the extraction module supports incremental updates, extracting only the changed parts of the scheme to reduce storage requirements.

[0101] In the shipboard scenario, the module only extracts changes in stiffness values, reducing data processing time. It's important to note that the extraction process must ensure data integrity. For example, a checksum can be used to verify whether a data stream is corrupted.

[0102] Step S51: Based on the parameter set, if the target adjustment value exceeds a preset threshold, the adjustment range is calculated by the logic judgment module in conjunction with the stiffness value, an adjustment command is generated, stored in the command queue, and the generated adjustment command set is determined. For example, a target adjustment value exceeding the preset threshold indicates that the component needs significant adjustment. For example, under high-intensity waves, the stiffness increment exceeds 30%. The logic judgment module calculates the specific adjustment range based on the stiffness value and the adjustment value.

[0103] In the breakwater scenario, the module calculates that the steel reinforcement tension needs to be increased to 600 kPa to meet the stiffness requirements. The adjustment command is generated in a standard format. For example, "Increase tension to 600 kPa for 5 seconds." The instruction is stored in an instruction queue, which is sorted by priority, with higher-priority instructions executed first. In one possible implementation, the logic judgment module combines multiple condition checks. For example, both stiffness and wave frequency can be considered simultaneously to ensure that the adjustment range is dynamically matched with the environment.

[0104] In the Yangtze River platform scenario, the module detected a wave frequency of 0.7 Hz, calculated that the required stiffness increment was 25%, and generated a corresponding command. It should be noted that the command queue supports dynamic updates; if environmental changes lead to the generation of new commands, the queue will be reordered to ensure that the latest commands are executed first.

[0105] Step S52: The adjustment execution unit obtains the adjustment instruction set, calls the control interface to send the adjustment instructions to the stressed component, completes the instruction execution, and obtains the response state of the stressed component. In one embodiment, the adjustment execution unit is connected to the stressed component through the control interface. For example, the tilt angle of the hull can be controlled by a servo motor.

[0106] Specifically, the control interface translates commands into concrete physical actions. For example, adjusting the motor speed or the pressure of the hydraulic system.

[0107] In a shipboard scenario, after receiving a command, the execution unit adjusts the deck angle to 5 degrees. Upon completion, it feeds back the current deformation state via sensors. The response state includes the actual stiffness value, deformation value, and adjustment time of the component.

[0108] In the breakwater scenario, after the actuator adjusted the panel stiffness, the sensor detected a deformation of 2 mm, which is in line with expectations. It should be noted that the device's response delay must be considered during the execution process. For example, starting a motor might take 0.3 seconds, and the system needs to reserve buffer time in the instructions. In another embodiment, the execution unit supports the parallel execution of multiple instructions. For example, the stiffness of multiple support columns can be adjusted simultaneously to cope with complex wave dynamics.

[0109] Step S53: Based on the response state, the deformation parameters of the stressed component are analyzed by the physical mapping module in conjunction with the stiffness value, stored in the deformation database, and the final deformation configuration is determined. For example, the physical mapping module calculates the final deformation parameters of the component by analyzing the deformation data and stiffness value in the response state.

[0110] In the Yangtze River platform scenario, the module calculates that the deformation distribution of the component is concentrated at the bottom of the support column based on a stiffness value of 5000 kN / m and a deformation data of 2 mm.

[0111] Specifically, the physical mapping module uses a geometric transformation method to map stiffness values ​​and deformation data to the physical model of the component, generating a deformation distribution map. Deformation parameters are stored in a matrix format in the deformation database. For example, "Position 1: Deformation 2 mm" and "Position 2: Deformation 1.5 mm". In one possible implementation, the mapping process combines the results of finite element analysis to verify the accuracy of the deformation parameters.

[0112] In the ship scenario, the module verifies that the deck deformation distribution is consistent with the simulation results, confirming the final deformation configuration. In another embodiment, the deformation database supports real-time updates, allowing the system to adjust deformation parameters based on new response states.

[0113] In the breakwater scenario, the database recorded that the panel deformation decreased from 3 mm to 1.8 mm, indicating a significant adjustment effect. The final deformation configuration was output as a 3D model, showcasing the deformation state of the component and providing a reference for subsequent maintenance. In one embodiment, the determination of the deformation configuration also needs to consider the long-term stability of the component.

[0114] In the Yangtze River platform scenario, after analyzing deformation parameters, the system predicts the fatigue life of components under continuous high-intensity waves, ensuring that the deformation configuration does not lead to material fatigue failure. It should be noted that the storage structure of the deformation database supports fast querying. For example, deformation data for a specific area can be retrieved using a location index. This approach improves the system's response efficiency and adapts to dynamically changing aquatic environments. The final deformation configuration provides data support for subsequent design optimizations. For example, by analyzing the deformation distribution, it can be determined whether additional support structures or adjustments to material selection are needed. In one possible implementation, the generation of deformation configurations incorporates multidimensional data analysis to ensure the adaptability of components under different wave intensities.

[0115] In nearshore breakwater scenarios, a deformation database records the deformation distribution of the panels under different wave frequencies. By analyzing this data, the system identifies the areas of concentrated deformation under high-frequency waves, and then adjusts the position and density of the support structure. It should be noted that determining the deformation configuration depends not only on the current wave dynamics but also on historical data to predict the long-term performance of the components.

[0116] The system can analyze deformation data from the past month to identify deformation trends in certain areas and provide early warnings of potential structural fatigue risks. This predictive method can significantly improve the safety of components and extend their service life.

[0117] Step S54: Based on the final deformation configuration, generate optimized design suggestions for the stressed components and store them in the design database to provide a reference for subsequent maintenance and improvement.

[0118] Specifically, the optimized design recommendations propose concrete improvement measures based on deformation configuration and stiffness distribution parameters. For example, increasing the number of support beams, adjusting the elastic modulus of the material, or changing the geometry of the component.

[0119] In the Yangtze River platform scenario, the system indicates a high deformation value at the bottom of the support column based on deformation configuration. It recommends adding auxiliary support columns in this area and increasing the material thickness by 10%. The optimized design recommendations are stored in the design database as a structured report, including a deformation distribution diagram, stiffness parameter adjustment suggestions, and expected effect analysis. It should be noted that the design database supports multi-user access, allowing engineering teams to quickly develop maintenance plans based on the recommendations. In one embodiment, the optimized design recommendations also include cost analysis. For example, comparing the cost of adding support columns with the benefits of extending the life of components.

[0120] In the marine setting, it is recommended to increase stiffness by adding deck support beams. Analysis shows that this measure can control deformation to within 1.5 mm, while increasing costs by only 5%. This approach achieves a balance between performance optimization and economy. In another embodiment, the optimized design recommendations are combined with environmental adaptability analysis to propose customized solutions for different aquatic environments.

[0121] In lake environments, waves have low frequencies but long durations; the system recommends using high-toughness materials to withstand prolonged low-frequency loading. In marine environments, waves are high-intensity and change rapidly; therefore, it is recommended to increase the number of dynamic adjustment devices to improve response speed. It should be noted that the generation of optimized design recommendations must consider the actual application scenario of the components. For example, ship decks need to prioritize weight limitations, while breakwaters focus more on impact resistance. The database storage structure should support scenario-based categorization. For example, data can be organized using tags such as "Yangtze River Platform," "Ships," and "Breakwater" to facilitate rapid retrieval and application. The generation and storage of optimized design recommendations provide a reliable basis for the long-term maintenance of components and can effectively reduce the risk of structural damage caused by environmental fluctuations.

[0122] Step S55: Periodically update the deformation database and design database, and optimize the generation logic of the dynamic adjustment scheme by combining real-time environmental data and historical data. For example, the updates to the deformation database and design database are implemented through scheduled tasks. For example, an incremental update is performed on the database every day at midnight. The update process obtains the latest wave dynamic data from the sensor array, compares it with historical data, and identifies trends in environmental changes.

[0123] In the nearshore area, the system detected a gradual increase in wave frequency over the past week, and the updated database recorded the new deformation distribution and stiffness requirements. It should be noted that the update logic also needs to consider data integrity. For example, data validation can be used to ensure the accuracy of new data. In one possible implementation, the update process incorporates anomaly detection algorithms to identify and remove abnormal data caused by sensor malfunctions.

[0124] In the Yangtze River platform scenario, if a sensor continuously outputs abnormally high wave height values, the system will automatically flag this data and prioritize the use of fused results from other sensors. The updated database provides more accurate data support for the generation of dynamic adjustment schemes. In another embodiment, the database update is combined with a machine learning model to optimize the logic for generating adjustment schemes.

[0125] The system analyzes historical deformation data and dynamic environmental parameters to train a predictive model that forecasts deformation trends over the next 24 hours. The model output is used to prioritize dynamic adjustment strategies. For example, when predicting high-intensity waves, schemes with larger stiffness increments are prioritized. This approach improves the foresight of the adjustment scheme and reduces response delays caused by sudden environmental changes.

[0126] In the breakwater scenario, the updated database shows that panel deformation tends to increase under high-frequency waves. Based on this, the system adjusts its control scheme, prioritizing increased steel reinforcement tension. It should be noted that the database update frequency can be adjusted according to the dynamics of the aquatic environment. For example, in storm-prone areas, the update frequency may be increased to once per hour. This dynamic update mechanism ensures that the system can adapt to environmental changes in real time, improving the accuracy and efficiency of adjustments.

[0127] Step S56: Based on the optimized dynamic adjustment scheme, a long-term maintenance plan is generated to guide the periodic inspection and performance evaluation of load-bearing components. In one embodiment, the long-term maintenance plan is based on data from the deformation database and the design database to formulate the inspection cycle and maintenance measures for the components.

[0128] In the Yangtze River platform scenario, it is recommended to conduct a comprehensive inspection of the support columns every 6 months, focusing on checking the material fatigue in areas of concentrated deformation.

[0129] Specifically, the maintenance plan includes the testing items, execution time, and expected results. For example, identifying microcracks inside support columns using ultrasonic testing could potentially extend component lifespan by 20%. Maintenance plans are stored as structured documents, containing detailed execution steps and resource requirements. In another possible implementation, the maintenance plan incorporates a risk assessment model to predict the probability of component failure under different environmental conditions.

[0130] In the marine scenario, the model predicts a 10% risk of deck failure under continuous high-intensity waves, and plans to increase stress testing to once a quarter based on this. It should be noted that the maintenance plan needs to be coordinated with the engineering team's requirements. For example, the plan can be transmitted to the enterprise's asset management system via an API interface. In one possible implementation, the long-term maintenance plan also includes contingency response plans for rapid repairs under extreme environmental conditions.

[0131] In the breakwater scenario, the plan stipulates that when the wave height exceeds 3 meters, emergency reinforcement measures should be initiated immediately, such as temporarily adding support beams or adjusting the panel angle. The emergency response plan is generated based on real-time environmental data and historical failure cases to ensure the measures are targeted and feasible.

[0132] System analysis of historical data revealed that breakwater deformation under high-intensity waves is concentrated at the joints; therefore, the emergency plan prioritizes reinforcing this area. It should be noted that the execution of the maintenance plan must be compatible with the hardware performance of the regulating device. For example, ensuring the servo motor's response speed meets the time requirements for emergency reinforcement. This comprehensive maintenance strategy can significantly improve the reliability and safety of components, adapting to complex and changing aquatic environments.

[0133] Step S57: Combining the dynamic adjustment scheme and maintenance plan, a performance evaluation report for the component is generated and stored in the evaluation database to provide data support for subsequent optimization. For example, the performance evaluation report comprehensively analyzes the component's operational status based on deformation configuration, stiffness distribution, and maintenance records.

[0134] In the Yangtze River platform scenario, the report shows that the support columns maintained stable deformation control under high-intensity waves over the past year, with a maximum deformation of 2.5 mm, which meets the design requirements.

[0135] Specifically, the evaluation report includes an analysis of the stress distribution, deformation trend, and adjustment effect of the component, presented in chart form. For example, a thermogram of deformation distribution or a trend chart of stiffness variation. In one embodiment, the report also includes a performance comparison analysis. For example, comparing the performance of the component before and after optimization shows that the deformation was reduced by 30% after optimization. It should be noted that the evaluation database supports multi-dimensional queries. For example, data can be retrieved by time, component type, or environmental conditions, making it easier for engineering teams to analyze the long-term performance of components. In another embodiment, the performance evaluation report incorporates predictive models to predict the performance of components under future environmental conditions.

[0136] In the marine scenario, the report predicts that the deck may experience slight deformation under high-intensity waves over the next six months, and recommends reinforcing the support structure in advance. The predictive model, based on historical data and real-time environmental parameters, uses time series analysis to generate performance trend curves.

[0137] The curve shows that deck deformation can increase by up to 3 mm during storm season, and the system makes preventative maintenance recommendations based on this. It should be noted that the report generation process must ensure the objectivity of the data. For example, multi-source data verification can avoid data bias from a single sensor. The storage structure of the evaluation report supports version management. For example, each update generates a new report version, making it easier to track changes in component performance. This approach provides a data foundation for continuous component optimization and can effectively address dynamic changes in the aquatic environment.

[0138] Step S58: Based on the performance evaluation report, optimize the deployment strategy of the sensor array to improve the accuracy and coverage of data acquisition. In one possible implementation, the deployment strategy of the sensor array is adjusted according to the deformation and stress distribution data in the performance evaluation report.

[0139] In the breakwater scenario, the report showed insufficient deformation data at the panel connection point. The system recommended adding an ultrasonic sensor in this area to improve the accuracy of data acquisition.

[0140] Specifically, optimization strategies include adjusting the location, number, and sampling frequency of sensors.

[0141] In the Yangtze River platform scenario, the number of sensors was increased from 10 to 15, focusing on covering the high-stress area at the base of the support columns. It should be noted that environmental interference must be considered during sensor deployment. For example, in nearshore areas, waves may be affected by topographic reflections, requiring additional sensors in reflective areas to capture complex wave dynamics. In another embodiment, optimization strategies are combined with coverage analysis to ensure that the sensor array covers key areas of the aquatic environment.

[0142] In a lake environment, the system analyzes wave propagation paths and adjusts sensor positions to cover the main wave propagation directions. The optimized deployment strategy improves the accuracy of environmental dynamic parameter acquisition, providing more reliable data support for subsequent analysis. In one embodiment, the optimization of the sensor array also needs to consider power consumption and maintenance costs.

[0143] In the Yangtze River platform scenario, the system analyzes the data contribution of sensors, prioritizing the retention of high-contribution sensors and reducing the use of inefficient sensors, thereby lowering energy consumption. The contribution analysis is based on the historical data output of the sensors. For example, if one sensor continuously provides high-precision wave height data and its contribution score is 0.9, while another sensor's score is only 0.4, the system may suggest replacing or removing the inefficient sensor. It should be noted that the optimization process also needs to ensure the redundancy of the sensor array. For example, backup sensors can be deployed in critical areas to address the risk of single points of failure. The optimized sensor deployment strategy is recorded in a database, including the location coordinates, sampling frequency, and expected lifespan of each sensor, facilitating subsequent maintenance and management. This approach strikes a balance between data accuracy and system cost, improving the overall system's operational efficiency.

[0144] Step S59: Based on the optimized sensor array, periodically verify the execution effect of the dynamic adjustment scheme and update the adjustment logic to adapt to long-term environmental changes. For example, the verification process evaluates the effectiveness of the scheme by comparing the environmental parameters after adjustment with preset optimization standards.

[0145] In a ship scenario, the system verifies whether the deformation of the deck after adjustment is controlled within 2 millimeters. If it does not meet the standard, the adjustment logic is adjusted.

[0146] Specifically, the verification process obtains the latest environmental dynamic parameters from the sensor array and compares them with data in the deformation database.

[0147] In the breakwater scenario, the verification panel deformation exceeded expectations even under high-intensity waves. Based on this, the system updated its adjustment logic, increasing the stiffness adjustment range. In one possible implementation, the verification process incorporates statistical analysis to calculate the confidence level of the adjustment effect.

[0148] The system analyzed deformation data from the past 10 adjustments, calculating an average deformation of 1.8 mm with a confidence level of 95%, indicating that the adjustment scheme is generally effective. It should be noted that the verification frequency was adjusted according to environmental dynamics. For example, in storm-prone areas, daily verification might be sufficient, while in calm lakes, weekly verification is enough. In another embodiment, the adjustment logic is updated using an incremental learning method, gradually optimizing based on the verification results.

[0149] In the Yangtze River platform scenario, the system detected high adjustment delays under high-frequency waves, and the update logic reduced the response time requirement from 3 seconds to 2 seconds. Incremental learning adjusts the weight parameters in the logic by analyzing the latest environmental data and adjustment effects. For example, increasing the weight of wave frequency on the adjustment amplitude. The updated adjustment logic is stored in the logic database, supporting version control. For example, each update generates a new logical version, facilitating backtracking and comparison. It should be noted that the update process must consider system stability. For example, simulation tests can be used to verify the effectiveness of new logic and avoid introducing instability factors. The optimized adjustment logic can better adapt to long-term environmental changes. For example, during seasonal storms, the system automatically prioritizes generating high-intensity control plans. This dynamic verification and update mechanism ensures the system's continuous adaptability, enabling it to cope with the complexity and uncertainty of the aquatic environment.

[0150] Step S510: Combining the optimized adjustment logic and maintenance plan, a dynamic performance monitoring scheme for the component is generated to track the component's operating status in real time. In one embodiment, the dynamic performance monitoring scheme generates an operating status report for the component based on real-time data from the sensor array and historical data from the deformation database.

[0151] In the Yangtze River platform scenario, the monitoring solution generates a status report every hour, which includes data on the deformation, stress, and stiffness of the support columns.

[0152] Specifically, the monitoring solution analyzes the dynamic response characteristics of components through real-time data stream processing. For example, an alarm mechanism is triggered when a sudden increase in deformation is detected. This alarm mechanism notifies the engineering team via SMS or email, prompting them to immediately check the component's status. In another possible implementation, the monitoring solution combines visualization tools to generate a dynamic performance dashboard for the component.

[0153] In a shipboard scenario, the instrument panel displays the deck deformation distribution as a 3D model, with color depth indicating the degree of deformation, allowing the engineering team to intuitively understand the component's condition. It's important to note that the monitoring solution must consider the real-time nature of the data. For example, a low-latency communication protocol ensures data transmission time is less than 0.5 seconds. In one embodiment, the dynamic performance monitoring scheme also includes predictive maintenance functionality, which predicts potential risks to components based on historical and real-time data.

[0154] In the breakwater scenario, the system predicts that the panel may experience excessive deformation due to high-intensity waves within the next three months, and the monitoring plan recommends reinforcing the connection points in advance. Predictive maintenance is achieved through a time series analysis model, which generates risk probabilities based on the deformation trend of the components and dynamic environmental parameters.

[0155] The model predicts a deformation risk probability of 15% for a certain area, and the system marks this area as a key monitoring target. It should be noted that the implementation of the monitoring plan must be compatible with the hardware performance of the control device. For example, ensuring the response speed of sensors and actuators supports real-time monitoring. The generation and execution of dynamic performance monitoring schemes can significantly improve the operational reliability of components and reduce unexpected damage caused by environmental fluctuations. Through the above steps, the system can generate and execute dynamic adjustment schemes based on dynamic parameters of the aquatic environment, optimizing the performance of stressed components and adapting to complex and ever-changing environmental fluctuations. The entire process, through the coordinated work of sensor arrays, data processing, numerical analysis, and dynamic adjustment, ensures the safety and stability of components under high-intensity waves. The optimized component performance can effectively cope with the dynamic changes in the aquatic environment, providing reliable technical support for marine engineering, ship design, and breakwater construction.

[0156] The present invention also provides an intelligent adjustment system for piers to resist wave impact, comprising: The perception layer includes an environmental perception and data processing module. This module uses sensor arrays (ultrasonic rangefinders, accelerometers, and current meters) deployed at key locations such as buoys and dock structures to acquire raw signals such as wave height, wave frequency, and wave velocity in real time. The module denoises and filters the raw signals, performs time-frequency analysis using Fourier transform to extract the wave's time-frequency characteristics, uses principal component analysis for dimensionality reduction to extract core feature vectors, and classifies the wave state using algorithms such as support vector machines. Finally, it integrates the classification results from multiple sensors to generate a comprehensive and highly reliable environmental dynamic parameter classification result, accurately determining the current wave state of the water area. The cognitive and decision-making layer includes a wave prediction and load analysis module, a structural health diagnosis and assessment module, and an intelligent decision-making and solution generation module. The wave prediction and load analysis module can predict future wave trends and their impact on the wharf based on current and historical data. The structural health diagnosis and assessment module is used to assess the health status of the wharf structure under current and predicted loads. The intelligent decision-making and solution generation module is used to formulate the optimal adjustment strategy based on the diagnostic results. The execution layer includes an instruction execution and dynamic adjustment module, which is used to put decisions into practice.

[0157] It should be noted that this module is activated when the environmental dynamic intensity exceeds a threshold. Using time series analysis algorithms and historical data, it simulates and predicts the trends in wave height, frequency, and velocity over a future period. Based on the predicted wave trends, it calculates the peak impact load distribution on the wharf's structural components (such as piles, decks, and mooring bollards) using physical models (e.g., the principle of energy conservation), including the magnitude and area of ​​force. Using finite element analysis tools, the predicted impact load is applied to the wharf's digital twin model to simulate the stress distribution of the structure, identifying local stress concentration areas. Dynamic simulation tools analyze the deformation and stiffness distribution of the structure under dynamic loads to determine its dynamic adjustment characteristics. Optimization tools such as genetic algorithms are used to adjust and evaluate the structural parameters, generating a quantitative evaluation index to objectively determine whether the current structural performance meets safety requirements. If the quantitative evaluation index fails to meet the standard, this module integrates historical and real-time environmental data to analyze the response time characteristics of the adjustment device (how quickly it needs to react). Using decision tree algorithms or rule engines, it generates a specific dynamic adjustment plan based on the environmental state and structural health diagnosis results. The solution includes the target adjustment value (such as the percentage increase in stiffness) and the specific stiffness value, and converts the adjustment solution into control commands that can be recognized by the adjustment execution unit (such as a hydraulic system or servo motor).

[0158] The adjustment execution unit receives control commands, drives the adjustment device (such as active support hydraulic cylinder, variable stiffness support, mass tuned damper, etc.) to perform physical actions, monitors the response state of the structure after adjustment (such as actual deformation and actual stiffness) in real time, and analyzes and determines the final deformation configuration of the structure through the physical mapping module.

[0159] The optimization and evolution layer includes a performance monitoring and system optimization module, which is used to compare the adjustment target with the actual effect and verify the effectiveness of the dynamic adjustment scheme.

[0160] It should be noted that the system can maintain and regularly update the deformation database, design database, and evaluation database, store data throughout the entire lifecycle, compare the adjustment targets with the actual effects, verify the effectiveness of dynamic adjustment schemes, adjust the position and density of the sensor array based on performance reports to improve data quality, optimize the wave prediction model and the generation logic of adjustment schemes using machine learning based on historical data, and generate long-term maintenance plans and performance evaluation reports based on long-term performance data, providing data support for preventive maintenance and design improvements at the wharf.

[0161] This system successfully transforms passive wave resistance into proactive, intelligent adaptive adjustment. It goes beyond simply assessing after wave impact; it predicts impacts, prepares in advance, adjusts in real time, and optimizes afterward, forming a complete intelligent operation and maintenance closed loop. This significantly improves the safety, durability, and operational efficiency of the terminal in complex and variable water environments.

[0162] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0163] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart adjustment method for resisting wave impact at a wharf, characterized in that, Includes the following steps: S1. Obtain environmental dynamic parameters from the aquatic environment through a sensor array. The environmental dynamic parameters include wave height, wave frequency, and wave speed. Process the parameters to obtain parameter classification results. S2. Determine the dynamic intensity of the environment based on the parameter classification results. If the dynamic intensity of the environment exceeds the preset intensity threshold, activate the prediction module to simulate the future dynamic change trend of the environment and determine the peak distribution of the impact load. S3. Based on the peak distribution of impact load, stress distribution analysis is performed on the stressed components. A numerical analysis model is used to calculate the matching degree between the current adjustment characteristics and stiffness distribution, and a quantitative evaluation index of optimization requirements is obtained. S4. If the quantitative evaluation index is lower than the preset optimization standard, the response time characteristics of the regulating device are judged by integrating historical environmental data and real-time dynamic environmental parameters through the information processing link, and a dynamic regulation scheme is generated. S4. Extract the target adjustment value and stiffness value from the dynamic adjustment scheme, send the adjustment command to the adjustment execution unit, and determine the deformation configuration of the stressed component.

2. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: Step S1 also includes: S11. Based on time-frequency eigenvalues, feature extraction is performed to generate feature vectors of wave parameters, and the main components of the feature vectors are determined. S12. If the main components of the feature vector exceed the preset threshold, the feature vector is classified by the support vector machine algorithm to obtain the classification result of the wave parameters. S13. Use data fusion methods to integrate the classification results of multiple sensor arrays, generate comprehensive environmental dynamic parameter classification results, and determine the intensity of water environment fluctuations.

3. The intelligent adjustment method for resisting wave impact at a wharf according to claim 2, characterized in that: The time-frequency characteristic values ​​in step S11 include the peak frequency, average amplitude, and velocity distribution of wave height; the preset threshold in step S12 is determined based on the characteristics of the aquatic environment.

4. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: Step S2 further includes: S21. Based on time series analysis algorithms and historical data, simulate the dynamic changes in the environment to obtain trend prediction results; S22. Calculate the peak distribution prediction based on the trend prediction results to determine the peak distribution of the impact load.

5. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: The time series analysis in step S21 uses an autoregressive model to predict wave dynamics over a future period based on the patterns of historical wave data. The autoregressive model analyzes the time series of wave height, frequency, and velocity to determine the autocorrelation of the data and generate trend predictions for the next few minutes or hours. In step S22, the peak distribution of impact load reflects the maximum force exerted by waves on the stressed components. The calculation process is based on the predicted wave height and velocity, combined with a physical model to determine the magnitude and distribution of the impact force.

6. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: Step S3 further includes: S31. If there are local stress concentration areas in the first stress distribution data, the optimized second stress distribution data can be obtained by adjusting the mesh density and material parameters and recalculating using a numerical analysis model. S32, Based on the second stress distribution data, a dynamic simulation tool is used to simulate the adjustment characteristics of the component. By comparing the simulation results with the preset performance threshold, the stiffness distribution parameters of the component are determined. S33 uses a genetic algorithm to adjust the parameters of the component based on the stiffness distribution parameters, obtains quantitative evaluation indicators, and determines whether the optimization requirements meet the preset performance requirements.

7. The intelligent adjustment method for resisting wave impact at a wharf according to claim 6, characterized in that: The local stress concentration areas in step S31 are identified by abnormally high stress values; in step S32, the dynamic simulation tool evaluates the deformation and stiffness characteristics of the component by simulating the dynamic response of the component under impact load; in step S33, the genetic algorithm optimizes the stiffness distribution parameters of the component by simulating the natural selection process.

8. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: Step S4 also includes: S41. Use database query tools to extract historical environmental data, and use stream processing tools to process real-time dynamic environmental parameters to obtain a comprehensive environmental dataset. S42. If the quantitative evaluation index of the comprehensive environmental dataset is lower than the preset optimization standard, the comprehensive environmental dataset is analyzed through the information processing link to determine the response time characteristics of the regulating device. S43. Use the decision tree algorithm to classify the comprehensive environmental dataset and determine the response time characteristics; S44. Generate a dynamic adjustment scheme based on the response time characteristics, and convert the dynamic adjustment scheme into control commands using a control command generation tool; S45. Use the rule engine to generate a dynamic adjustment scheme based on the response time characteristics to obtain control instructions; S46. Execute control commands through the adjustment device to adjust environmental parameters to meet preset optimization standards; S47. Use automated control tools to send control commands to the regulating device to complete the adjustment of environmental parameters; The database query tool in step S41 extracts historical wave data from a preset database, including time series of wave height, frequency, and speed. The information processing step in step S42 analyzes the comprehensive environmental dataset to evaluate the response speed and effectiveness of the control device in the current environment. The decision tree algorithm in step S43 generates classification rules based on the characteristics of the comprehensive environmental dataset, such as wave height, frequency, and response time requirements. The dynamic adjustment scheme in step S44 is based on response time characteristics to determine the specific actions of the adjustment device, such as adjusting the angle of the servo motor or the pressure of the hydraulic system. The rule engine in step S45 generates an adjustment scheme based on a preset rule base and combined with response time characteristics. The rule base contains a mapping relationship between various environmental conditions and adjustment actions. The adjustment device in step S46 includes a servo motor, a hydraulic system, or a robotic arm, and performs specific adjustment actions according to control commands. In step S47, the automation control tool transmits instructions to the regulating device through an industrial control protocol.

9. The intelligent adjustment method for resisting wave impact at a wharf according to claim 1, characterized in that: Step S5 further includes: S51. According to the parameter set, if the target adjustment value exceeds the preset threshold, the adjustment range is calculated by combining the stiffness value with the logic judgment module, an adjustment command is generated, stored in the command queue, and the generated adjustment command set is determined. S52. Obtain the adjustment instruction set through the adjustment execution unit, call the control interface to send the adjustment instructions to the stressed component, complete the instruction execution, and obtain the response status of the stressed component; S53. Based on the response status, the deformation parameters of the stressed component are analyzed by combining the stiffness value with the physical mapping module, stored in the deformation database, and the final deformation configuration is determined. S54. Based on the final deformation configuration, generate optimized design suggestions for the stressed components and store them in the design database; S55. Regularly update the deformation database and design database, and optimize the generation logic of dynamic adjustment schemes by combining real-time environmental data and historical data. S56. Based on the optimized dynamic adjustment scheme, generate a long-term maintenance plan to guide the periodic inspection and performance evaluation of load-bearing components; S57. Combine the dynamic adjustment scheme and maintenance plan to generate a performance evaluation report for the component and store it in the evaluation database; S58. Based on the performance evaluation report, optimize the deployment strategy of the sensor array to improve the accuracy and coverage of data acquisition; S59. Based on the optimized sensor array, periodically verify the execution effect of the dynamic adjustment scheme and update the adjustment logic to adapt to long-term environmental changes. S510, combining the optimized adjustment logic and maintenance plan, generates a dynamic performance monitoring scheme for the component, and tracks the operating status of the component in real time.

10. An intelligent adjustment system for resisting wave impact at a wharf, characterized in that: include: The perception layer includes an environmental perception and data processing module. This module acquires raw wave height, wave frequency, and wave speed signals in real time through sensor arrays deployed at key locations on buoys and wharf structures. It then performs noise reduction and filtering on the raw signals and performs time-frequency analysis using Fourier transform to extract the time-frequency characteristics of the waves. Principal component analysis is used for dimensionality reduction to extract core feature vectors, and wave states are classified using algorithms such as support vector machines. The classification results from multiple sensors are integrated to generate environmental dynamic parameter classification results, accurately determining the wave state of the current water area. The cognitive and decision-making layer includes a wave prediction and load analysis module, a structural health diagnosis and assessment module, and an intelligent decision-making and solution generation module. The wave prediction and load analysis module can predict future wave trends and their impact on the wharf based on current and historical data. The structural health diagnosis and assessment module is used to assess the health status of the wharf structure under current and predicted loads. The intelligent decision-making and solution generation module is used to formulate the optimal adjustment strategy based on the diagnostic results. The execution layer includes an instruction execution and dynamic adjustment module, which is used to put decisions into practice. The optimization and evolution layer includes a performance monitoring and system optimization module, which is used to compare the adjustment target with the actual effect and verify the effectiveness of the dynamic adjustment scheme.

Images