Intelligent monitoring system for wharf breakwater

Abstract

The invention relates to the technical field of structural health monitoring, in particular to a wharf breakwater intelligent monitoring system which comprises a multi-modal data acquisition module, a data preprocessing module, a stress prediction module, a structural health assessment module, a self-adaptive early warning module and a remote monitoring and maintenance management module. A plurality of data such as sound waves, vibration, pressure, temperature and corrosion are collected in real time, data cleaning, denoising and standardization processing are carried out, a sparse auto-encoder model is used for extracting low-dimensional sparse features, the breakwater stress change trend is analyzed, and a comprehensive report of stress distribution, crack propagation, corrosion loss and structural fatigue is generated through structural health assessment. The early warning threshold value is dynamically adjusted through a self-adaptive early warning mechanism, an early warning notice is sent to a manager, the remote monitoring and maintenance management module supports real-time monitoring and remote configuration and scheduling of maintenance management of the breakwater, the structural safety of the breakwater is improved, the service life is prolonged, and the management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of structural health monitoring, and in particular to an intelligent monitoring system for a wharf breakwater. Background Art

[0002] As an important coastal protection structure, the main function of the wharf breakwater is to resist the invasion of natural forces such as waves and storms, and protect the safety of ports, ships and shore facilities. However, the breakwater is exposed to the harsh marine environment for a long time and is easily affected by various factors, such as seawater corrosion, wind and wave impact, structural fatigue and material aging. These problems will cause cracks, stress concentration, corrosion loss and other hidden dangers in the breakwater structure, seriously threatening its stability and service life. Therefore, structural health monitoring and maintenance management of the breakwater are crucial to its long-term stable operation.

[0003] Existing breakwater monitoring technologies mainly rely on traditional sensor data collection and manual periodic inspections, which have obvious technical limitations. First, the data collection of traditional sensors can only cover a single or limited dimension, and cannot achieve comprehensive monitoring of the breakwater structure. Secondly, the data processing technology is relatively simple and cannot fully utilize the useful information in the massive sensor data, resulting in key issues such as stress distribution, crack expansion, and corrosion loss. It is difficult to accurately predict. The existing system lacks an intelligent stress prediction model and an adaptive early warning mechanism, and cannot dynamically respond to changes in complex environments. The early warning mechanism is not sensitive enough and is prone to false alarms or missed alarms. Summary of the invention

[0004] Based on the above objectives, the present invention provides an intelligent monitoring system for dock breakwaters.

[0005] The intelligent monitoring system for the wharf breakwater includes a multimodal data acquisition module, a data preprocessing module, a stress prediction module, a structural health assessment module, an adaptive early warning module and a remote monitoring and maintenance management module, among which; The multimodal data acquisition module is used to collect multimodal data related to the health status of the breakwater structure, and the multimodal data includes sound waves, stress, vibration, corrosion, temperature and pressure data; The data preprocessing module is used to clean, denoise and unify the format of multimodal data; The stress prediction module extracts representative low-dimensional sparse features from multimodal data based on the sparse autoencoder algorithm, analyzes the stress change trend of the breakwater structure, and identifies potential stress anomalies and high-risk areas from multimodal data by learning the sparse characteristics of the data, and predicts future stress distribution based on historical data; The structural health assessment module assesses the overall structural health of the breakwater based on the analysis results of the stress prediction module, including stress distribution, crack propagation, corrosion loss and structural fatigue, and generates a comprehensive health assessment report of the breakwater in combination with historical data; The adaptive early warning module sets a dynamic early warning threshold based on the results of the structural health assessment module and the breakwater stress prediction trend. When the structural health assessment results and stress prediction exceed the predetermined safety threshold, the system automatically triggers the early warning mechanism, sends an early warning notification to the management personnel, and generates response suggestions; The remote monitoring and maintenance management module is used for management personnel to remotely access the monitoring system, view the structural health status of the breakwater in real time, and support remote configuration of sensor parameters, update of analysis algorithms, and dispatch of maintenance personnel.

[0006] Optionally, the multimodal data acquisition module includes multiple sensors for collecting different types of data related to the health status of the breakwater structure, specifically including: Acoustic sensor: used to detect the impact of waves and the conduction of sound waves inside the structure, and collect data on the propagation speed, frequency and sound intensity of sound waves; Visual sensors: including underwater cameras and drone-mounted cameras, which are used to collect visual data on the breakwater surface and inside the structure to monitor crack growth and corrosion; Vibration sensor: used to measure the vibration frequency, amplitude and acceleration of the breakwater structure under the action of waves and wind; Pressure sensor: used to measure pressure changes inside and outside the breakwater, including instantaneous pressure caused by wave impact and long-term pressure distribution; Temperature sensor: used to measure the temperature of seawater and air, as well as the temperature changes of breakwater materials; Electrochemical sensor: used to monitor the corrosion of breakwater materials and collect corrosion data of breakwater materials, including steel corrosion potential and corrosion rate.

[0007] Optionally, the data preprocessing module specifically includes: Data cleaning: Clean the collected multimodal data to remove incomplete, abnormal or damaged data points; Denoising: A denoising algorithm based on wavelet transform is used to suppress the noise in multimodal data; Format unification processing: Data from different sensors are processed in a unified format.

[0008] Optionally, the stress prediction module extracts representative low-dimensional sparse features from the multimodal data based on a sparse autoencoder algorithm, specifically including: Build model: Build a sparse autoencoder model based on the sparse autoencoder algorithm Data input: input the real-time multimodal data preprocessed by the data preprocessing module into the sparse autoencoder model; Low-dimensional sparse feature extraction: The sparse autoencoder model extracts representative low-dimensional sparse features from multimodal data.

[0009] Optionally, the stress prediction module predicts future stress distribution and analyzes stress trends based on the extracted low-dimensional sparse features, specifically including: Historical data retrospective analysis: retrospectively analyze the historical multimodal data collected and analyze the stress change patterns of the breakwater at different periods of time; Establishment of stress distribution prediction model: Establish a stress distribution prediction model based on historical multimodal data and extracted sparse features; Stress trend prediction: Based on the prediction results of the stress distribution prediction model, analyze the stress change trend of the breakwater structure in the future; Marking of stress abnormal points: The system automatically marks the stress abnormal points in the prediction results and generates a dangerous area report to prompt managers to take preventive maintenance measures.

[0010] Optionally, the structural health assessment module assesses the stress distribution of the breakwater, specifically including: Stress distribution analysis: Based on the low-dimensional sparse features generated by the stress prediction module, the stress distribution of each area of ​​the breakwater is systematically analyzed. Through the stress distribution map, stress concentration areas and dangerous locations are identified, especially those areas that are exposed to environmental changes for a long time; Stress threshold comparison: Compare the real-time predicted stress data with the preset safety threshold to detect whether there are abnormal areas in the stress distribution that exceed the threshold. If the stress in a certain area exceeds the preset safety threshold, the system will mark it as a potential danger area. Historical data review: Combine past stress historical data, compare current stress distribution with historical change trends, and evaluate the long-term and stability of stress changes.

[0011] Optionally, the structural health assessment module performs a comprehensive assessment of crack propagation, corrosion loss and structural fatigue, specifically including: Crack extension assessment: Using visual sensor data, image analysis algorithms are used to monitor crack extension on the breakwater surface and internal structure. Based on the changes in crack width and length in the image and combined with stress distribution results, the further extension trend of the crack is predicted. Corrosion loss assessment: Based on the corrosion data of breakwater materials collected by electrochemical sensors, the corrosion status of breakwater materials, including corrosion rate and corrosion depth, is assessed; Structural fatigue assessment: By analyzing the data from vibration sensors and pressure sensors, combined with historical stress data, the structural fatigue state of the breakwater is assessed; Health assessment report generation: Generate a health assessment report for the breakwater based on comprehensive analysis results of stress distribution, crack propagation, corrosion loss and structural fatigue.

[0012] Optionally, the adaptive warning module sets a dynamic warning threshold based on the structural health assessment result and the stress prediction trend, specifically including: Dynamic threshold adjustment: Based on the stress distribution, crack extension, corrosion loss and structural fatigue parameters provided by the structural health assessment module, the system automatically adjusts the warning threshold. The setting of the warning threshold takes into account the dynamic changes of environmental conditions, such as tides, temperature, wind speed and other factors, to ensure the accuracy of the warning; Threshold update algorithm: The warning threshold is dynamically adjusted according to the changes in real-time data; Dangerous area monitoring: Combining the stress concentration area identification and historical data in the stress prediction module, the dangerous area is marked according to the dynamic warning threshold. If the stress level in a certain area continues to increase and approaches the threshold, the system will conduct real-time monitoring and activate the early warning mechanism.

[0013] Optionally, when the warning mechanism is triggered, the adaptive warning module sends a warning notification to the management personnel, specifically including: Multi-level warning mechanism: When the structural health assessment results or stress prediction exceed the set dynamic warning threshold, multi-level warnings are automatically triggered. The first-level warning is used for minor over-limit situations to remind management personnel to monitor; the second-level warning is for serious over-limit situations, and the system will recommend temporary reinforcement or other preventive measures; Early warning notification: Send real-time early warning notifications to managers through multiple channels. Early warning notifications are sent in a variety of ways, such as SMS, APP push and email; Generation of response suggestions: When an alert is triggered, the system automatically generates response suggestions based on the health assessment report and stress prediction trends.

[0014] Optionally, the remote monitoring and maintenance management module specifically includes: Remote real-time monitoring: Managers can remotely access the intelligent monitoring system platform of the wharf breakwater through the Internet to view the structural health status of the breakwater in real time; Remote sensor parameter configuration: The system allows managers to remotely adjust the working parameters of each sensor; Remote algorithm update: The system supports remote update of data analysis and stress prediction algorithms; Maintenance personnel scheduling: When the system triggers an alarm or the management personnel detect an abnormality, the remote monitoring and maintenance management module automatically generates maintenance tasks; Historical data storage and report generation: The system regularly stores monitoring data, health assessment results and maintenance records in a cloud database for management personnel to query.

[0015] Beneficial effects of the present invention: In the present invention, through the multimodal data acquisition module, the system can simultaneously collect data from multiple angles such as acoustics, vision, vibration, pressure, temperature and electrochemistry in real time, and clean, denoise and standardize these multi-source data through the data preprocessing module, thereby ensuring the accuracy and integrity of the data and providing high-quality basic data for stress prediction and health assessment. The stress prediction module based on the sparse autoencoder model can extract low-dimensional sparse features related to structural stress changes from high-dimensional data, accurately predict the stress distribution and future change trend of the breakwater structure, and improve the efficiency and accuracy of data analysis.

[0016] The present invention uses a structural health assessment module to comprehensively analyze multi-dimensional information such as stress distribution, crack expansion, corrosion loss and structural fatigue, generate a health assessment report for the breakwater, and comprehensively assess its current health status and future potential risks. Combined with an adaptive early warning module, the system can dynamically adjust the early warning threshold according to real-time stress distribution and health assessment results to ensure the sensitivity and accuracy of the early warning mechanism. When the safety threshold is exceeded, the multi-level early warning system can promptly issue early warning notifications to management personnel and provide detailed response suggestions, significantly improving the response efficiency and management intelligence level of breakwater maintenance.

[0017] The present invention provides managers with a remote real-time monitoring and visual interface for the breakwater structure status through the remote monitoring and maintenance management module, and supports remote configuration of sensor parameters and remote update of data analysis algorithms. Managers can not only keep track of the health of the breakwater at any time, but also remotely dispatch maintenance teams, optimize maintenance processes, and ensure rapid response after early warnings are triggered. The system also has historical data storage and report generation functions, which help managers conduct long-term trend analysis and maintenance decisions, and improve the long-term safety management efficiency of the breakwater. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention; Figure 2 Schematic diagram of the stress prediction module process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0021] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0022] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0023] like Figure 1-Figure 2 As shown, the intelligent monitoring system for the wharf breakwater includes a multimodal data acquisition module, a data preprocessing module, a stress prediction module, a structural health assessment module, an adaptive early warning module and a remote monitoring and maintenance management module, wherein; The multimodal data acquisition module is used to collect multimodal data related to the health status of the breakwater structure, including acoustic wave, stress, vibration, corrosion, temperature and pressure data; The data preprocessing module is used to clean, denoise and format the multimodal data; The stress prediction module extracts representative low-dimensional sparse features from multimodal data based on the sparse autoencoder algorithm to analyze the stress change trend of the breakwater structure. The sparse autoencoder identifies potential stress anomalies and high-risk areas from multimodal data by learning the sparse characteristics of the data, and predicts future stress distribution based on historical data; The structural health assessment module evaluates the overall structural health of the breakwater based on the analysis results of the stress prediction module. The assessment content includes stress distribution, crack propagation, corrosion loss and structural fatigue, and generates a comprehensive health assessment report of the breakwater in combination with historical data; The adaptive early warning module sets dynamic early warning thresholds based on the results of the structural health assessment module and the breakwater stress prediction trend. When the structural health assessment results and stress prediction exceed the predetermined safety threshold, the system automatically triggers the early warning mechanism, sends an early warning notification to the management personnel, and generates detailed response suggestions; The remote monitoring and maintenance management module is used for managers to remotely access the monitoring system and view the structural health status of the breakwater in real time. It also supports remote configuration of sensor parameters, updating of analysis algorithms, and scheduling of maintenance personnel.

[0024] The multimodal data acquisition module includes multiple sensors for collecting different types of data related to the health status of the breakwater structure, including: Acoustic sensor: used to detect the impact of waves and the conduction of sound waves inside the structure, and collect data on the propagation speed, frequency and sound intensity of sound waves; Visual sensors: including underwater cameras and drone-mounted cameras, which are used to collect visual data on the breakwater surface and inside the structure to monitor crack growth and corrosion; Vibration sensor: used to measure the vibration frequency, amplitude and acceleration of the breakwater structure under the action of waves and wind; Pressure sensor: used to measure pressure changes inside and outside the breakwater, including instantaneous pressure caused by wave impact and long-term pressure distribution; Temperature sensor: used to measure the temperature of seawater and air, as well as the temperature changes of breakwater materials; Electrochemical sensor: used to monitor the corrosion of breakwater materials and collect corrosion data of breakwater materials, including steel bar corrosion potential and corrosion rate; By integrating multiple types of sensors, the multimodal data acquisition module can comprehensively cover the key data required for breakwater health monitoring, provide real-time data on structural stress, corrosion and environmental changes, and ensure the diversity and accuracy of the monitoring system.

[0025] The data preprocessing module specifically includes: Data cleaning: Clean the collected multimodal data (including sound waves, stress, vibration, corrosion, temperature and pressure data) to remove incomplete, abnormal or damaged data points to ensure the integrity and accuracy of the data. By setting a reasonable threshold range, the noise data that exceeds the threshold range can be automatically filtered out; Denoising: A denoising algorithm based on wavelet transform is used to suppress the noise in multimodal data. Wavelet transform decomposes the original data into different frequency components, identifies and removes high-frequency noise. The denoising algorithm formula is expressed as: ; in, is the denoised signal, are the frequency components of the original signal, is the wavelet basis function; Format unification: Data from different sensors (such as acoustic data, visual data, vibration data, etc.) are formatted in a unified manner so that all types of data can be converted into comparable numerical types and time series for subsequent model analysis and processing. The unified data format ensures the consistency of timestamps, units, and dimensions of all data inputs. The data preprocessing module ensures the integrity, accuracy and consistency of input data through data cleaning, denoising and format unification, providing high-quality basic data for subsequent stress prediction and health assessment.

[0026] The stress prediction module extracts representative low-dimensional sparse features from multimodal data based on the sparse autoencoder algorithm, including: Build model: Build a sparse autoencoder model based on the sparse autoencoder algorithm Data input: The real-time multimodal data preprocessed by the data preprocessing module is input into the sparse autoencoder model. The data types include vibration, pressure, temperature, corrosion, etc.; Low-dimensional sparse feature extraction: The sparse autoencoder model extracts representative low-dimensional sparse features from multimodal data. The specific steps include: (1) Multimodal data input: The sensor data (including vibration, pressure, temperature, corrosion, etc.) obtained from the multimodal data acquisition module is input into the sparse autoencoder model in matrix form. The input matrix is ​​recorded as ; (2) Encoder part: The encoder of the sparse autoencoder converts high-dimensional input data Mapping to a low-dimensional sparse feature space is achieved through one or more layers of neural networks. The goal of the encoder is to compress high-dimensional data into low-dimensional data through linear transformation and activation function. Sparsity is achieved through regularization. The output formula of the encoder is expressed as: ; in, is a low-dimensional sparse feature matrix, is the weight matrix of the encoder, is the bias term, is the activation function; (3) Sparse regularization: To ensure that the output of the encoder is sparse, a sparse regularization constraint is introduced. At each node of the neural network, the number of activated neurons is controlled by the sparsity constraint term so that the output of most nodes is close to zero. The sparse regularization formula is expressed as: ; in, The encoder layer The output of the node, To control the regularization coefficient of sparsity, the sparse regularization term enables the model to retain only the key features related to stress prediction and reduce redundant information; (4) Decoder part: The task of the decoder is to extract low-dimensional sparse features. Reconstruct the original input Output of the same scale , through one or more layers of neural networks, the decoder tries to minimize the reconstruction error, expressed as: ; in, is the reconstructed data, is the weight matrix of the decoder, is the bias term; (5) Loss function calculation: The training goal of the sparse autoencoder is to minimize the total loss function of the reconstruction error and the sparse regularization term. The total loss function is expressed as: ; in, and are the input data and the reconstructed data respectively, is the number of samples, is a sparse feature, is the sparsity control coefficient. By minimizing this loss function, the sparse autoencoder can extract the most representative low-dimensional sparse features. (6) Feature output: After training, the encoder extracts sparse features Representing the key information related to the stress changes of the breakwater structure in the multimodal data, these features can be used for stress trend analysis and anomaly detection, and provide input for the structural health assessment module.

[0027] The stress prediction module predicts future stress distribution and analyzes stress trends based on the extracted low-dimensional sparse features, including: Historical data retrospective analysis: Retrospectively analyze the stress change patterns of the breakwater at different times by retrospecting the collected historical multimodal data. Match these historical data with real-time low-dimensional sparse features to find out the stress concentration areas and change trends of the breakwater under specific conditions. Establishment of stress distribution prediction model: Based on historical multimodal data and extracted sparse features, a stress distribution prediction model is established. The model is expressed as: ; in, For time The predicted stress value of is the stress influence coefficient matrix, For time The sparse features of is the bias term; Stress trend prediction: Based on the prediction results of the stress distribution prediction model, analyze the stress change trend of the breakwater structure in the future period of time, identify potential stress concentration areas and high-risk points by dynamically updating the prediction results, and make adjustments based on future environmental changes to ensure the accuracy of the prediction; Abnormal stress point marking: The system automatically marks abnormal stress points in the prediction results and generates a dangerous area report to prompt managers to take preventive maintenance measures; The stress prediction module accurately predicts the future stress distribution and change trend of the breakwater through historical data analysis and stress distribution prediction model, timely identifies potential stress anomalies and high-risk areas, and provides data support for preventive maintenance of the breakwater.

[0028] The structural health assessment module evaluates the stress distribution of the breakwater, including: Stress distribution analysis: Based on the low-dimensional sparse features generated by the stress prediction module, the stress distribution of each area of ​​the breakwater is systematically analyzed. Through the stress distribution map, stress concentration areas and dangerous locations are identified, especially those areas that are exposed to environmental changes for a long time; Stress threshold comparison: Compare the real-time predicted stress data with the preset safety threshold to detect whether there are abnormal areas in the stress distribution that exceed the threshold. If the stress in a certain area exceeds the preset safety threshold, the system will mark it as a potential danger area, prompting management personnel to pay special attention. Historical data review: Combine past stress historical data to compare current stress distribution with historical change trends, evaluate the long-term and stability of stress changes, help identify the growth trend of stress concentration areas, and assess whether the structure is at risk of gradual deterioration; The structural health assessment module evaluates the stress distribution of the breakwater by analyzing stress prediction results and historical data, helps identify stress concentration areas and dangerous locations, and provides data support for preventive maintenance.

[0029] The structural health assessment module provides a comprehensive assessment of crack growth, corrosion loss and structural fatigue, including: Crack extension assessment: Using visual sensor data, image analysis algorithms are used to monitor crack extension on the breakwater surface and internal structure. Based on the changes in crack width and length in the image and combined with stress distribution results, the further extension trend of the crack is predicted. Corrosion loss assessment: Based on the corrosion data of breakwater materials collected by electrochemical sensors, the corrosion status of breakwater materials, including corrosion rate and corrosion depth, is assessed. Combined with stress distribution analysis, areas with severe corrosion are identified and the impact of these areas on the overall structural health is assessed; Structural fatigue assessment: By analyzing the data from vibration sensors and pressure sensors, combined with historical stress data, the structural fatigue state of the breakwater is assessed. The system compares the fatigue assessment results with the current stress distribution to determine whether the structure has reached its fatigue limit or is close to failure. Health assessment report generation: Based on the comprehensive analysis results of stress distribution, crack propagation, corrosion loss and structural fatigue, a health assessment report of the breakwater is generated. The report summarizes the current status of the breakwater, identifies areas that require key maintenance, and provides maintenance recommendations; The structural health assessment module accurately evaluates the crack expansion, corrosion loss and structural fatigue condition of the breakwater through multi-dimensional comprehensive analysis, providing comprehensive and reliable data support for the long-term maintenance and safety management of the breakwater.

[0030] The adaptive warning module sets dynamic warning thresholds based on the structural health assessment results and stress prediction trends, including: Dynamic threshold adjustment: Based on the stress distribution, crack extension, corrosion loss and structural fatigue parameters provided by the structural health assessment module, the system automatically adjusts the warning threshold. The setting of the warning threshold takes into account the dynamic changes of environmental conditions, such as tides, temperature, wind speed and other factors, to ensure the accuracy of the warning; Threshold update algorithm: The warning threshold is dynamically adjusted according to the changes in real-time data. The threshold update algorithm is expressed as: ; in, For time Dynamic warning threshold at is the basic threshold, is the current stress distribution, is the environmental variation parameter, is the sensitivity coefficient, is a function based on stress prediction trend; Dangerous area monitoring: Combined with the stress concentration area identification and historical data in the stress prediction module, dangerous areas are marked according to the dynamic warning threshold. If the stress level in a certain area continues to increase and approaches the threshold, the system will conduct real-time monitoring and activate the warning mechanism; The adaptive early warning module can monitor changes in the structural health status in real time by dynamically adjusting the early warning threshold, effectively identify potential danger areas, and provide a flexible early warning mechanism for the safety management of breakwaters.

[0031] When the early warning mechanism is triggered, the adaptive early warning module sends an early warning notification to the management personnel, including: Multi-level warning mechanism: When the structural health assessment results or stress prediction exceed the set dynamic warning threshold, multi-level warnings are automatically triggered. The first-level warning is used for minor over-limit situations to remind management personnel to monitor; the second-level warning is for serious over-limit situations, and the system will recommend temporary reinforcement or other preventive measures; Early warning notification: Real-time early warning notifications are sent to managers through multiple channels. The notifications include detailed information such as the warning area, exceeded parameters, and recommended maintenance actions. Early warning notifications are sent through multiple methods, such as SMS, APP push, and email, to ensure that managers can respond in time; Response suggestion generation: When an early warning is triggered, the system automatically generates detailed response suggestions based on the health assessment report and stress prediction trend. The suggestions include specific maintenance measures, reinforcement plans, regular monitoring time intervals, etc., to provide decision support for managers; The adaptive early warning module automatically triggers a multi-level early warning mechanism and generates detailed response suggestions to ensure that the breakwater can be monitored and maintained in a timely manner when stress exceeds the limit, thereby improving the safety of the structure and the level of intelligent management.

[0032] The remote monitoring and maintenance management module specifically includes: Remote real-time monitoring: Managers can remotely access the intelligent monitoring system platform of the wharf breakwater through the Internet to view the structural health status of the breakwater in real time. The system provides a user-friendly interface to display the current stress distribution, crack extension, corrosion loss, structural fatigue and overall health assessment report. Users can select a specific time period for data retrospective analysis and view historical change trends; Remote sensor parameter configuration: The system allows managers to remotely adjust the working parameters of each sensor, such as sampling frequency, sensitivity and data transmission interval. Managers can flexibly adjust sensor configurations based on real-time monitoring data or system warning results to optimize data collection accuracy and frequency. Remote algorithm update: The system supports remote update of data analysis and stress prediction algorithms. Managers can upload new algorithm models to the monitoring platform through the cloud based on system requirements or research results. The system automatically deploys the updated analysis model and applies it to the analysis and processing of real-time data. Maintenance personnel scheduling: When the system triggers an alarm or the management personnel detect an abnormality, the remote monitoring and maintenance management module automatically generates a maintenance task. The system analyzes the alarm level, abnormal location and equipment status, intelligently schedules the most suitable maintenance team, and sends a task notification to the relevant personnel. The notification content includes the maintenance location, problem description and recommended maintenance measures; Historical data storage and report generation: The system regularly stores monitoring data, health assessment results and maintenance records in a cloud database for management personnel to query. Management personnel can generate customized health reports to analyze the long-term health trend of the breakwater and support long-term maintenance decisions of the breakwater; The remote monitoring and maintenance management module helps managers efficiently understand the structural health status of the breakwater and take timely response measures through remote real-time monitoring, flexible sensor parameter configuration, algorithm updates, and intelligent maintenance scheduling, thereby improving the intelligence and remote management capabilities of the system.

[0033] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0034] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Intelligent monitoring system for wharf breakwater, characterized by: It includes multimodal data acquisition module, data preprocessing module, stress prediction module, structural health assessment module, adaptive early warning module and remote monitoring and maintenance management module, among which; The multimodal data acquisition module is used to collect multimodal data related to the health status of the breakwater structure, and the multimodal data includes sound waves, stress, vibration, corrosion, temperature and pressure data; The data preprocessing module is used to clean, denoise and unify the format of multimodal data; The stress prediction module extracts representative low-dimensional sparse features from multimodal data based on the sparse autoencoder algorithm, analyzes the stress change trend of the breakwater structure, and identifies potential stress anomalies and high-risk areas from multimodal data by learning the sparse characteristics of the data, and predicts future stress distribution based on historical data; The structural health assessment module assesses the overall structural health of the breakwater based on the analysis results of the stress prediction module, including stress distribution, crack propagation, corrosion loss and structural fatigue, and generates a comprehensive health assessment report of the breakwater in combination with historical data; The adaptive early warning module sets a dynamic early warning threshold based on the results of the structural health assessment module and the breakwater stress prediction trend. When the structural health assessment results and stress prediction exceed the predetermined safety threshold, the system automatically triggers the early warning mechanism, sends an early warning notification to the management personnel, and generates response suggestions; The remote monitoring and maintenance management module is used for management personnel to remotely access the monitoring system, view the structural health status of the breakwater in real time, and support remote configuration of sensor parameters, update of analysis algorithms, and dispatch of maintenance personnel.

2. The intelligent monitoring system for dock breakwater according to claim 1 is characterized in that: The multimodal data acquisition module includes multiple sensors for collecting different types of data related to the health status of the breakwater structure, specifically including: Acoustic sensor: used to detect the impact of waves and the conduction of sound waves inside the structure, and collect data on the propagation speed, frequency and sound intensity of sound waves; Visual sensors: including underwater cameras and drone-mounted cameras, which are used to collect visual data on the breakwater surface and inside the structure to monitor crack growth and corrosion; Vibration sensor: used to measure the vibration frequency, amplitude and acceleration of the breakwater structure under the action of waves and wind; Pressure sensor: used to measure pressure changes inside and outside the breakwater, including instantaneous pressure caused by wave impact and long-term pressure distribution; Temperature sensor: used to measure the temperature of seawater and air, as well as the temperature changes of breakwater materials; Electrochemical sensor: used to monitor the corrosion of breakwater materials and collect corrosion data of breakwater materials, including steel corrosion potential and corrosion rate.

3. The intelligent monitoring system for dock breakwater according to claim 2 is characterized in that: The data preprocessing module specifically includes: Data cleaning: Clean the collected multimodal data to remove incomplete, abnormal or damaged data points; Denoising: A denoising algorithm based on wavelet transform is used to suppress the noise in multimodal data; Format unification processing: Data from different sensors are processed in a unified format.

4. The intelligent monitoring system for dock breakwater according to claim 3 is characterized in that: The stress prediction module extracts representative low-dimensional sparse features from multimodal data based on the sparse autoencoder algorithm, specifically including: Build model: Build a sparse autoencoder model based on the sparse autoencoder algorithm; Data input: input the real-time multimodal data preprocessed by the data preprocessing module into the sparse autoencoder model; Low-dimensional sparse feature extraction: The sparse autoencoder model extracts representative low-dimensional sparse features from multimodal data.

5. The intelligent monitoring system for dock breakwater according to claim 4 is characterized in that: The stress prediction module predicts future stress distribution and analyzes stress trends based on the extracted low-dimensional sparse features, specifically including: Historical data retrospective analysis: retrospectively analyze the historical multimodal data collected and analyze the stress change patterns of the breakwater at different periods of time; Establishment of stress distribution prediction model: Establish a stress distribution prediction model based on historical multimodal data and extracted sparse features; Stress trend prediction: Analyze the stress change trend of the breakwater structure based on the prediction results of the stress distribution prediction model; Marking of stress abnormal points: The system automatically marks the stress abnormal points in the prediction results and generates a dangerous area report to prompt managers to take preventive maintenance measures.

6. The intelligent monitoring system for dock breakwater according to claim 5 is characterized in that: The structural health assessment module evaluates the stress distribution of the breakwater, specifically including: Stress distribution analysis: Based on the low-dimensional sparse features generated by the stress prediction module, the stress distribution of each area of ​​the breakwater is systematically analyzed, and stress concentration areas and dangerous locations are identified through stress distribution maps; Stress threshold comparison: Compare the real-time predicted stress data with the preset safety threshold to detect whether there are abnormal areas in the stress distribution that exceed the threshold. If the stress in a certain area exceeds the preset safety threshold, the system will mark it as a potential danger area. Historical data review: Combine past stress historical data, compare current stress distribution with historical change trends, and evaluate the long-term and stability of stress changes.

7. The intelligent monitoring system for dock breakwater according to claim 5 is characterized in that: The structural health assessment module conducts a comprehensive assessment of crack propagation, corrosion loss and structural fatigue, specifically including: Crack extension assessment: Using visual sensor data, image analysis algorithms are used to monitor crack extension on the breakwater surface and internal structure. Based on the changes in crack width and length in the image and combined with stress distribution results, the further extension trend of the crack is predicted. Corrosion loss assessment: Based on the corrosion data of breakwater materials collected by electrochemical sensors, the corrosion status of breakwater materials, including corrosion rate and corrosion depth, is assessed; Structural fatigue assessment: By analyzing the data from vibration sensors and pressure sensors, combined with historical stress data, the structural fatigue state of the breakwater is assessed; Health assessment report generation: Generate a health assessment report for the breakwater based on comprehensive analysis results of stress distribution, crack propagation, corrosion loss and structural fatigue.

8. The intelligent monitoring system for dock breakwater according to claim 7 is characterized in that: The adaptive warning module sets dynamic warning thresholds based on the structural health assessment results and stress prediction trends, specifically including: Dynamic threshold adjustment: The system automatically adjusts the warning threshold according to the stress distribution, crack extension, corrosion loss and structural fatigue parameters provided by the structural health assessment module; Threshold update algorithm: The warning threshold is dynamically adjusted according to the changes in real-time data; Dangerous area monitoring: Combining the stress concentration area identification and historical data in the stress prediction module, the dangerous area is marked according to the dynamic warning threshold. If the stress level in a certain area continues to increase and approaches the threshold, the system will conduct real-time monitoring and activate the early warning mechanism.

9. The intelligent monitoring system for dock breakwater according to claim 8 is characterized in that: When the warning mechanism is triggered, the adaptive warning module sends a warning notification to the management personnel, specifically including: Multi-level warning mechanism: When the structural health assessment results or stress prediction exceed the set dynamic warning threshold, multi-level warnings are automatically triggered; Early warning notification: Send real-time early warning notifications to managers through multiple channels. Early warning notifications are sent in multiple ways; Generation of response suggestions: When an alert is triggered, the system automatically generates response suggestions based on the health assessment report and stress prediction trends.

10. The intelligent monitoring system for dock breakwater according to claim 9, characterized in that: The remote monitoring and maintenance management module specifically includes: Remote real-time monitoring: Managers can remotely access the intelligent monitoring system platform of the wharf breakwater through the Internet to view the structural health status of the breakwater in real time; Remote sensor parameter configuration: The system allows managers to remotely adjust the working parameters of each sensor; Remote algorithm update: The system supports remote update of data analysis and stress prediction algorithms; Maintenance personnel scheduling: When the system triggers an alarm or the management personnel detect an abnormality, the remote monitoring and maintenance management module automatically generates maintenance tasks; Historical data storage and report generation: The system regularly stores monitoring data, health assessment results and maintenance records in a cloud database for management personnel to query.

Images