Seawater exchange breakwater protection performance evaluation system and disaster warning system

Abstract

The present invention discloses a seawater exchange breakwater protection performance evaluation system and a disaster warning system, which specifically relate to the field of marine engineering technology. The breakwater is divided into a number of monitoring areas, seawater exchange parameters in different time periods in each area are obtained, the seawater exchange parameters are classified and weighted, and the overall protection performance coefficient of the breakwater is obtained after weighted average calculation. According to the calculation result, the protection performance is divided into normal protection and abnormal protection. The energy reduction effect of the breakwater is evaluated by real-time monitoring of the energy changes of incident and transmitted waves. Fuzzy logic is used to predict and warn disaster risks based on the overall protection performance coefficient and energy reduction changes. Comprehensive evaluation and timely warning of the breakwater protection performance are achieved, thereby improving the protection effect of the breakwater and the safety of the coastal environment.

Description

Technical Field

[0001] The invention relates to the technical field of marine engineering, and in particular to a seawater exchange type breakwater protection performance evaluation system and a disaster early warning system. Background Art

[0002] Seawater exchange breakwater protection and disaster warning refers to a new type of breakwater system that aims to improve the protection performance and ecological benefits of breakwaters through optimized design and advanced technical means. The system not only accurately evaluates the protection effect of breakwaters against waves through intelligent sensors and real-time data analysis, but also promotes the effective exchange of seawater inside and outside the breakwater by dynamically adjusting the structure to avoid water quality deterioration and ecological damage. This design ensures that the breakwater not only provides physical protection, but also maintains the healthy and sustainable development of seawater exchange.

[0003] In terms of disaster warning, the system uses sensor networks and data processing technology to monitor changes in seawater exchange in real time. When the system detects potential disaster risks (such as storm surges or tsunamis), it can quickly analyze data and issue warning signals to remind relevant departments and personnel to take preventive measures. This will not only improve the response speed of breakwaters when disasters occur, but also minimize potential losses and harm, ensuring the safety of coastal areas.

[0004] The prior art has the following deficiencies:

[0005] In the existing technology, the physical model may not be able to fully simulate the complex situation in the actual seawater exchange. It cannot accurately reflect the real characteristics of the waves and their impact on the breakwater, resulting in large deviations in the evaluation results. In addition, the signal source of the existing early warning system is single. When the evaluation results of the physical model are distorted, the accuracy of the early warning signal may be affected, resulting in false alarms or missed alarms. Summary of the invention

[0006] The purpose of the present invention is to provide a seawater exchange breakwater protection performance evaluation system and a disaster warning system to solve the shortcomings of the background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a seawater exchange breakwater protection performance evaluation system, comprising a data acquisition module, a data analysis module, a protection performance classification module and a visualization module;

[0008] Data acquisition module: divides the breakwater into several monitoring areas, obtains the seawater exchange parameters in different time periods in each monitoring area, and sends the obtained seawater exchange parameters to the data analysis module;

[0009] Data analysis module: classify according to the type of seawater exchange parameters, identify and analyze the changing trends of seawater flow rate and water quality, determine the weighted values ​​of seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater based on the weighted average of the seawater exchange parameters in each monitoring area;

[0010] Protection performance division module: According to the calculation results, the overall protection performance of the breakwater is divided into normal protection and abnormal protection, and the division results are sent to the visualization module;

[0011] Visualization module: Prepare a protection performance evaluation report based on the division results of the overall protection performance coefficient and the overall protection performance of the breakwater, and perform a visual display.

[0012] In a preferred embodiment, the seawater exchange parameters include analyzing the changing trend of seawater flow rate data to obtain the seawater flow rate anomaly index, analyzing the changing trend of water quality parameters to obtain the water quality parameter deviation value.

[0013] In a preferred embodiment, the method for obtaining the seawater flow velocity anomaly index is:

[0014] The seawater velocity data within the time period t is obtained, and the obtained seawater velocity data is standardized, and the seawater velocity data is used to construct a time series {Yt}, and the time series Yt is decomposed into a trend component Tt, a seasonal component St, and a residual component Rt.

[0015] The decomposed residual component Rt is extracted to identify abnormal seawater velocity data. The mean μR and standard deviation σR of the residual component are calculated respectively, and the standard threshold λ of seawater velocity under standard conditions is obtained. The abnormal seawater data is identified and analyzed. If |Rt-μR|>λ*σR, Rt is abnormal seawater data. The abnormal seawater data is analyzed and the seawater velocity anomaly index is calculated. The specific calculation expression is: Where LK is the seawater velocity anomaly index.

[0016] In a preferred embodiment, the method for obtaining the water quality parameter deviation value is:

[0017] Preprocess the water quality parameters obtained in real time, including dissolved oxygen, pH value, conductivity and salinity; select the isolation forest algorithm, prepare a training data set, including all preprocessed water quality parameter time series data, use the isolation forest algorithm to train the model, learn the normal water quality parameter data pattern, define the number of trees in the forest, and the number of samples used to train each tree. Use the trained isolation forest model to calculate the anomaly score of each data point. The specific model calculation expression is: Where h(X, i) is the path length of the i-th tree to the data point X, n is the number of trees in the forest, i is the tree number, AS(X) is the anomaly score of each data point, and the water quality parameter deviation value is calculated based on the anomaly score of each data point. The specific calculation expression is: DV = |AS(X)-AS(X m )|; where DV is the water quality parameter deviation value, AS(X m ) is the anomaly score at time m.

[0018] In a preferred embodiment, the seawater flow rate anomaly index and the water quality parameter deviation value are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the weighted assignment label of the seawater exchange parameters in each monitoring area as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the seawater exchange parameters in all monitoring areas as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weighted assignment of the seawater exchange parameters in each monitoring area is determined according to the model output results, and the weighted average calculation of the weighted assignment labels of the seawater exchange parameters in each monitoring area is performed to calculate the overall protection performance coefficient.

[0019] In a preferred embodiment, the acquired overall protection performance coefficient is compared with a reference threshold of the overall protection performance. If the overall protection performance coefficient is greater than or equal to the reference threshold of the overall protection performance, it is classified as normal protection and no immediate measures are needed. If the overall protection performance coefficient is less than the reference threshold of the overall protection performance, it is classified as abnormal protection and further investigation of the cause is required and corresponding improvement measures need to be taken.

[0020] The present invention also provides a seawater exchange breakwater disaster early warning system, including a data acquisition module, a data analysis module, an energy reduction analysis module and a risk prediction module:

[0021] Data acquisition module: divide the breakwater into several monitoring areas and obtain the seawater exchange parameters in different time periods in each monitoring area;

[0022] Data analysis module: classify the seawater exchange parameters according to their types, determine the weights of the seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater after weighted average;

[0023] Energy reduction analysis module: real-time monitoring and measurement of incident and transmitted wave energy, to determine the change in the reduction of wave energy by the breakwater;

[0024] Risk prediction module: Based on the changes in the overall protection performance coefficient and wave energy reduction, disaster risk prediction and early warning are carried out by using fuzzy logic.

[0025] In a preferred embodiment, in the energy reduction analysis module, the wave height and energy are continuously monitored by a wave height sensor, and the wave energy at each moment is calculated by the incident wave and the transmitted wave data at each time point. The stability of the wave energy at each time point is analyzed to obtain the wave energy stability value. The wave energy stability value is obtained by:

[0026] The wave energy at each moment is calculated through the incident wave and transmitted wave data at each time point. The specific calculation expression is: In the formula, E t is the wave energy at each moment, ρ is the water density, g is the acceleration due to gravity, and H is the wave height;

[0027] Set the time window size to w, determine the number of time points included in each calculation of the wave energy stability value, calculate the wave energy average μt in each window, and for each time point t, calculate the wave energy average in the window [t-w+1, t]; and the wave energy standard deviation σt in the window [t-w+1, t]; calculate the wave energy stability value based on the calculated wave energy average and standard deviation in each window. The specific calculation expression is: Where AQ is the stable value of wave energy.

[0028] In a preferred embodiment, the overall protection performance coefficient and the wave energy stability value are used as input items, and the disaster warning level is used as an output item;

[0029] Define fuzzy sets for overall protection performance coefficient and wave energy stability value, and define fuzzy sets for disaster risk;

[0030] Establish fuzzy rules and use fuzzy reasoning methods to determine the disaster risk level;

[0031] The specific numerical value is fuzzified, the fuzzy rules are input for reasoning, and the fuzzy reasoning results are defuzzified to obtain the specific risk level.

[0032] In a preferred embodiment, when the risk level is high, a first-level warning signal is generated and an emergency response mechanism is initiated; when the risk level is medium, a second-level warning signal is generated and monitoring is strengthened; when the risk level is low, a third-level warning signal is generated and routine maintenance is performed.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0034] 1. The present invention monitors the seawater exchange parameters and wave energy changes in each monitoring area of ​​the breakwater in real time, accurately calculates the overall protection performance coefficient and wave energy stability value, and uses fuzzy logic to predict and warn of disaster risks, thus overcoming the limitations of physical models and the single warning signal in the prior art. Through a graded warning mechanism, the emergency response mechanism is activated when the risk is high, monitoring is strengthened when the risk is medium, and routine maintenance is performed when the risk is low, ensuring the accuracy and timeliness of the warning, and effectively improving the protection effect of the breakwater and the safety of the coastal environment.

[0035] 2. The present invention can not only comprehensively monitor and analyze the complex situations in actual seawater exchange and provide more accurate protection performance evaluation, but also timely discover and respond to potential problems through multi-source data fusion and dynamic analysis, and ensure the long-term stability and reliability of breakwaters under different environmental conditions. Finally, through intuitive visualization and graded early warning signals, it provides a scientific basis for management and decision-making, significantly improving the disaster prevention and mitigation capabilities and environmental protection level of coastal areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0037] Figure 1 This is the module diagram of the seawater exchange breakwater protection performance evaluation system.

[0038] Figure 2 This is the module diagram of the seawater exchange breakwater disaster warning system. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example 1

[0041] See also Figure 1 As shown, the seawater exchange breakwater protection performance evaluation system described in this embodiment includes a data acquisition module, a data analysis module, a protection performance classification module and a visualization module;

[0042] Data acquisition module: divides the breakwater into several monitoring areas, obtains the seawater exchange parameters in different time periods in each monitoring area, and sends the obtained seawater exchange parameters to the data analysis module;

[0043] Data analysis module: classify according to the type of seawater exchange parameters, identify and analyze the changing trends of seawater flow rate and water quality, determine the weighted values ​​of seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater based on the weighted average of the seawater exchange parameters in each monitoring area;

[0044] Protection performance division module: According to the calculation results, the overall protection performance of the breakwater is divided into normal protection and abnormal protection, and the division results are sent to the visualization module;

[0045] Visualization module: Prepare a protection performance evaluation report based on the division results of the overall protection performance coefficient and the overall protection performance of the breakwater, and perform a visual display.

[0046] In the data acquisition module, the breakwater is divided into several monitoring areas, and the seawater exchange parameters in different time periods in each monitoring area are obtained, and the obtained seawater exchange parameters are sent to the data analysis module. According to the length and shape of the breakwater, the breakwater is divided into several monitoring areas.

[0047] Considering the structural characteristics of the breakwater, differences in seawater exchange, and key protection areas, the number and boundaries of the monitoring areas should be reasonably determined. Each monitoring area should be numbered to facilitate subsequent data management and analysis. A corresponding relationship between the area number and the geographical location should be established to form a regional division map.

[0048] Select appropriate types of sensors, including wave sensors, flow sensors, and water quality sensors, based on monitoring needs. Install sensors at key locations within each monitoring area to ensure comprehensive coverage of seawater exchange parameters in the area. Ensure that the sensors are installed in a stable and secure location to avoid interference from environmental factors. Calibrate all sensors to ensure accuracy and consistency of measurement data.

[0049] Set the sampling frequency of the sensor, determine the time interval for data collection according to the monitoring requirements (such as every 5 minutes, every hour), and collect the seawater exchange parameters in each monitoring area in real time. Transmit the sensor data to the data acquisition module in real time through the wireless communication device. Ensure the stability and reliability of the data transmission process to avoid data loss and delay. Store the real-time collected data in the data storage device and classify and store them according to the monitoring area and time sequence. Clean the data, remove outliers and noise, and fill in missing data. Convert the raw data into a standardized format to facilitate subsequent data analysis and processing. And send the acquired seawater exchange parameters to the data analysis module.

[0050] Data analysis module: Classify according to the type of seawater exchange parameters, identify and analyze the changing trends of seawater flow rate and water quality, determine the weighted values ​​of seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater based on the weighted average of the weighted values ​​of seawater exchange parameters in each monitoring area.

[0051] Seawater exchange parameters can be divided into five categories: physical parameters, chemical parameters, biological parameters, meteorological parameters, and hydrogeological parameters. Classifying seawater exchange parameters by type can help monitor and analyze seawater exchange more systematically, and support real-time data collection and subsequent analysis and processing. Through this subdivision, it is possible to more effectively identify and predict the trend of seawater exchange changes, and provide a scientific basis for the evaluation of breakwater protection performance and ecological environmental protection.

[0052] Specific seawater exchange parameters include seawater flow rate anomaly index and water quality parameter deviation value.

[0053] Among them, the specific seawater exchange parameters include analyzing the changing trend of seawater flow rate data to obtain the seawater flow rate anomaly index, analyzing the changing trend of water quality parameters to obtain the water quality parameter deviation value.

[0054] The method for obtaining the seawater velocity anomaly index is as follows:

[0055] The seawater velocity data within the time period t is obtained, and the obtained seawater velocity data is standardized, and the seawater velocity data is used to construct a time series {Yt}, and the time series Yt is decomposed into a trend component Tt, a seasonal component St, and a residual component Rt.

[0056] The decomposed residual component Rt is extracted to identify abnormal seawater velocity data. The mean μR and standard deviation σR of the residual component are calculated respectively, and the standard threshold λ of seawater velocity under standard conditions is obtained. The abnormal seawater data is identified and analyzed. If |Rt-μR|>λ*σR, Rt is abnormal seawater data. The abnormal seawater data is analyzed and the seawater velocity anomaly index is calculated. The specific calculation expression is: Where LK is the seawater velocity anomaly index.

[0057] The larger the anomaly index of seawater velocity, the more significant anomalies in the seawater velocity in the area where the breakwater is located, which may reflect the weaker protection ability of the breakwater in dealing with extreme seawater exchange. Abnormal flow velocity may cause the breakwater structure to bear greater pressure, affecting its stability and effectiveness.

[0058] High anomaly index may expose problems in the design or maintenance of breakwaters. For example, the design of the breakwater fails to fully consider the extreme changes in seawater velocity, or the breakwater has not been effectively maintained and monitored during long-term use, resulting in weakened protection performance.

[0059] The greater the abnormal seawater velocity index, the higher the potential disaster risk that abnormal flow velocity may bring. This may include increased coastal erosion, damage to port facilities, and flooding in inland areas. Therefore, breakwaters need to be urgently evaluated and improved to enhance their protection capabilities under extreme marine conditions and ensure the safety of coastal areas.

[0060] Among them, the method for obtaining the water quality parameter deviation value is:

[0061] Preprocess the water quality parameters obtained in real time, including dissolved oxygen, pH value, conductivity and salinity;

[0062] Select the Isolation Forest algorithm, prepare a training dataset containing all preprocessed water quality parameter time series data, train the model using the Isolation Forest algorithm, learn the normal water quality parameter data patterns, define the number of trees in the forest, and the number of samples used to train each tree, which is usually set to a fraction of the dataset size (such as 256).

[0063] Use the trained isolation forest model to calculate the anomaly score of each data point. The specific model calculation expression is: Where h(X, i) is the path length of the i-th tree to the data point X, n is the number of trees in the forest, i is the tree number, AS(X) is the anomaly score of each data point, and the water quality parameter deviation value is calculated based on the anomaly score of each data point. The specific calculation expression is: DV = |AS(X)-AS(X m )|; where DV is the water quality parameter deviation value, AS(X m ) is the anomaly score at time m.

[0064] The larger the deviation value of the water quality parameter, the more significant abnormal changes in the water quality in the area where the breakwater is located, which usually indicates that the overall protection performance of the breakwater is poor. The breakwater fails to effectively prevent the spread of pollutants or fails to maintain stable water quality, resulting in a decline in water quality. This may be due to design defects or poor maintenance of the breakwater, which cannot cope with the impact of environmental pressures and pollution sources.

[0065] Significant deviations in water quality parameters usually mean that there have been abnormal changes in the chemical or physical properties of the water body, such as a sharp drop in dissolved oxygen, abnormal fluctuations in pH, or a sharp increase in pollutant concentrations. In this case, the breakwater fails to effectively protect the marine ecological environment, which may lead to eutrophication of the water body, excessive algae growth, and a decrease in marine biodiversity. This deterioration of the ecological environment reflects the inadequacy of the breakwater in environmental protection.

[0066] The seawater flow rate anomaly index and the water quality parameter deviation value are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the weighted assignment label of the seawater exchange parameters in each monitoring area with each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the weighted assignment labels of the seawater exchange parameters in all monitoring areas as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weighted assignment of the seawater exchange parameters in each monitoring area is determined according to the model output results, and the overall protection performance coefficient is calculated after the weighted average calculation of the weighted assignment labels of the seawater exchange parameters in each monitoring area.

[0067] The method for obtaining the weighted values ​​of the seawater exchange parameters in each monitoring area is as follows: from the first eigenvector training data of the trained machine learning model, the corresponding function expression is obtained: WT=f1(DV, LK); wherein f1 is the output function of the model, DV is the water quality parameter deviation value, LK is the seawater flow rate anomaly index, and WT is the weighted value of the seawater exchange parameters in each monitoring area.

[0068] Protection performance division module: According to the calculation results, the overall protection performance of the breakwater is divided into normal protection and abnormal protection, and the division results are sent to the visualization module;

[0069] The obtained overall protection performance coefficient is compared with the reference threshold of the overall protection performance. If the overall protection performance coefficient is greater than or equal to the reference threshold of the overall protection performance, it means that the overall protection performance of the breakwater is good, and it is classified as normal protection without immediate measures; if the overall protection performance coefficient is less than the reference threshold of the overall protection performance, it means that the overall protection performance of the breakwater is poor, and it is classified as abnormal protection. Further investigation of the cause is required and corresponding improvement measures should be taken, and the classification results should be sent to the visualization module.

[0070] Visualization module: Prepare a protection performance evaluation report based on the division results of the overall protection performance coefficient and the overall protection performance of the breakwater, and perform a visual display.

[0071] In the evaluation report, the calculated overall protection performance coefficient and the reference threshold are compared in detail to clarify the protection performance level of the breakwater. The conclusion summarizes the evaluation results of the protection performance and puts forward corresponding improvement suggestions, such as strengthening routine maintenance, increasing the monitoring frequency or improving the breakwater structure design.

[0072] Use visualization tools to generate a variety of charts to intuitively display analysis results:

[0073] Time series graph: shows the changing trend of the deviation values ​​of each water quality parameter over time, helping to identify abnormal fluctuations and long-term changes.

[0074] Overall protection performance coefficient diagram: compares the overall protection performance coefficient with the reference threshold to intuitively display the protection performance classification results.

[0075] Spatial distribution map: Use geographic information system (GIS) to display the water quality parameter deviation values ​​and protection performance classification results of different monitoring points, reflecting the spatial distribution characteristics.

[0076] In this embodiment, the breakwater is divided into several monitoring areas, the seawater exchange parameters in different time periods in each monitoring area are obtained, the seawater exchange parameters are classified according to their types, the changing trends of seawater flow rate and water quality are identified and analyzed, the weighted values ​​of the seawater exchange parameters in the monitoring area are determined, and the overall protection performance coefficient of the breakwater is calculated by weighted average according to the weighted values ​​of the seawater exchange parameters in each monitoring area. The overall protection performance of the breakwater is divided into normal protection and abnormal protection, and the division results are sent to the visualization module; the overall protection performance coefficient and the division results of the overall protection performance of the breakwater are compiled into a protection performance evaluation report and visualized. This enables managers to quickly understand the operating status and potential problems of the breakwater, thereby optimizing protection measures and improving the overall protection capacity and environmental management level of the breakwater.

[0077] Example 2

[0078] See also Figure 2 As shown, the seawater exchange breakwater disaster warning system described in this embodiment includes a data acquisition module, a data analysis module, an energy reduction analysis module and a risk prediction module:

[0079] Data acquisition module: divide the breakwater into several monitoring areas and obtain the seawater exchange parameters in different time periods in each monitoring area;

[0080] Data analysis module: classify the seawater exchange parameters according to their types, determine the weights of the seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater after weighted average;

[0081] Energy reduction analysis module: real-time monitoring and measurement of incident and transmitted wave energy, to determine the change in the reduction of wave energy by the breakwater;

[0082] Risk prediction module: Based on the changes in the overall protection performance coefficient and wave energy reduction, disaster risk prediction and early warning are carried out by using fuzzy logic.

[0083] In the energy reduction analysis module, the energy of incident and transmitted waves is monitored and measured in real time to determine the change in the reduction of wave energy by the breakwater, specifically:

[0084] Real-time monitoring and measurement of incident and transmitted wave energy refers to the continuous monitoring of wave height and energy through wave height sensors installed in front and behind the breakwater. These sensors can capture the incident and transmitted wave data at each point in time, thereby calculating the wave energy at each moment. Through real-time data transmission, the system can immediately process and analyze this information to generate a time series of incident and transmitted energy.

[0085] Judging the change in the wave energy reduction of the breakwater means calculating the energy reduction rate and analyzing its change over time based on real-time monitoring data. This process can identify the protective effect of the breakwater under different environmental conditions, such as its performance under different tides, weather and wave conditions. Through continuous monitoring and analysis of the energy reduction rate, it is possible to evaluate whether the protective performance of the breakwater is stable, and to promptly identify and solve potential problems to ensure the long-term effectiveness and reliability of the breakwater.

[0086] The wave height and energy are continuously monitored by wave height sensors. The wave energy at each moment is calculated by the incident wave and transmitted wave data at each time point. The stability of the wave energy at each time point is analyzed to obtain the wave energy stability value. The method for obtaining the wave energy stability value is as follows:

[0087] The wave energy at each moment is calculated through the incident wave and transmitted wave data at each time point. The specific calculation expression is: In the formula, E t is the wave energy at each moment, ρ is the water density, g is the acceleration due to gravity, and H is the wave height;

[0088] Set the time window size to w, and determine the number of time points included in each calculation of the wave energy stability value; the selection of w should be determined according to the frequency of actual data and the needs of analysis, and calculate the average wave energy μt in each window. For each time point t, calculate the average wave energy in the window [t-w+1, t]; and the standard deviation of wave energy σt in the window [t-w+1, t]; calculate the wave energy stability value based on the calculated wave energy average and standard deviation in each window. The specific calculation expression is: Where AQ is the stable value of wave energy.

[0089] Risk prediction module: Based on the changes in the overall protection performance coefficient and wave energy reduction, disaster risk prediction and early warning are carried out by using fuzzy logic.

[0090] The overall protection performance coefficient and wave energy stability value are used as input items, and the disaster warning level is used as output item;

[0091] Define fuzzy sets (such as "low", "medium", "high") for the overall protection performance factor and wave energy stability value.

[0092] Define fuzzy sets for disaster risk (e.g., “low risk,” “medium risk,” “high risk”).

[0093] Fuzzy rule establishment:

[0094] A fuzzy rule is established that if the overall protection performance coefficient is “low” and the wave energy stability value is “low”, the disaster risk is “high risk”.

[0095] If the overall protection performance coefficient is "medium" and the wave energy stability value is "medium", the disaster risk is "medium risk".

[0096] If the overall protection performance factor is "high" and the wave energy stability value is "high", the disaster risk is "low risk".

[0097] Use fuzzy reasoning methods (such as Mamdani fuzzy reasoning) to perform reasoning and determine the disaster risk level.

[0098] Fuzzify the specific value and input the fuzzy rules for reasoning. Defuzzify the fuzzy reasoning results to get the specific risk level.

[0099] Based on the results of fuzzy logic analysis, the disaster risk level (such as "low risk", "medium risk", "high risk") is determined.

[0100] When the disaster type of the breakwater is high risk, a first-level warning signal is generated, and the emergency response mechanism is immediately activated to strengthen the real-time monitoring of the breakwater and the surrounding environment, strengthen the reinforcement and maintenance of the breakwater to prevent it from failing under extreme conditions. Arrange engineering and technical personnel to conduct emergency inspections and repairs on the breakwater.

[0101] When the disaster type of the breakwater is medium risk, a second-level warning signal is generated to strengthen the real-time monitoring of the breakwater, especially the monitoring of key parts. The breakwater is inspected and maintained in advance to ensure that it can perform at its maximum efficiency when a disaster strikes.

[0102] When the disaster type of the breakwater is low risk, a level 3 warning signal is generated and daily monitoring continues to ensure the safety of the breakwater and surrounding environment. Routine inspections and maintenance are carried out to ensure the structural integrity and protective effect of the breakwater.

[0103] In this embodiment, the height and energy of the incident and transmitted waves are monitored and continuously measured in real time by wave height sensors installed in front and behind the breakwater, the wave energy and its stable value at each moment are calculated, and the change of the energy reduction rate is analyzed. The sliding window size is set, the average value and standard deviation of the wave energy are calculated, and the wave energy stable value is obtained. Based on the overall protection performance coefficient and the wave energy stable value, fuzzy logic is used to predict the disaster risk. The two are used as input items, and the disaster risk level is inferred by establishing fuzzy rules (such as "low", "medium", and "high"), and the corresponding warning signal is generated according to the risk level: the first-level warning signal starts the emergency response mechanism, the second-level warning signal strengthens real-time monitoring, and the third-level warning signal performs routine inspections and maintenance to ensure the protection effect of the breakwater and the safety of the surrounding environment.

[0104] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0105] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0106] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0107] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0108] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0109] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. Seawater exchange breakwater protection performance evaluation system, characterized by: It includes data acquisition module, data analysis module, protection performance classification module and visualization module; Data acquisition module: divides the breakwater into several monitoring areas, obtains the seawater exchange parameters in different time periods in each monitoring area, and sends the obtained seawater exchange parameters to the data analysis module; Data analysis module: classify according to the type of seawater exchange parameters, identify and analyze the changing trends of seawater flow rate and water quality, determine the weighted values ​​of seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater by weighted average based on the weighted values ​​of seawater exchange parameters in each monitoring area; the seawater exchange parameters include the seawater flow rate anomaly index and the water quality parameter deviation value; Specifically, the seawater exchange parameters include analyzing the change trend of the seawater flow rate data to obtain the seawater flow rate anomaly index. The method for obtaining the seawater flow rate anomaly index is as follows: Obtain seawater velocity data within time period t, standardize the acquired seawater velocity data, and construct a time series of seawater velocity data , decompose the time series Yt into trend component Tt, seasonal component St and residual component Rt, extract the decomposed residual component Rt, and use it to identify abnormal seawater velocity data. Calculate the mean μR and standard deviation σR of the residual component, obtain the standard threshold λ of seawater velocity under standard conditions, and identify and analyze abnormal seawater data. ,but For abnormal seawater data, the abnormal seawater data is analyzed and the seawater velocity abnormality index is calculated. The specific calculation expression is: Where, LK is the abnormal seawater velocity index; Analyze the changing trend of water quality parameters and obtain the deviation value of water quality parameters. The method for obtaining the deviation value of water quality parameters is as follows: preprocess the water quality parameters obtained in real time, where the water quality parameters specifically include dissolved oxygen, pH value, conductivity and salinity; select the isolation forest algorithm, prepare a training data set, including all preprocessed water quality parameter time series data, use the isolation forest algorithm to train the model, learn the normal water quality parameter data pattern, define the number of trees in the forest, and the number of samples used to train each tree. Use the trained isolation forest model to calculate the anomaly score of each data point. The specific model calculation expression is: ; In the formula, is the path length of the i-th tree to the data point X, n is the number of trees in the forest, i is the tree number, The abnormal score of each data point is used to calculate the water quality parameter deviation value. The specific calculation expression is: ; Where DV is the water quality parameter deviation value, is the anomaly score at time m; Protection performance division module: According to the calculation results, the overall protection performance of the breakwater is divided into normal protection and abnormal protection, and the division results are sent to the visualization module; Visualization module: Prepare a protection performance evaluation report based on the division results of the overall protection performance coefficient and the overall protection performance of the breakwater, and perform a visual display.

2. The seawater exchange breakwater protection performance evaluation system according to claim 1 is characterized in that: The seawater flow rate anomaly index and the water quality parameter deviation value are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the weighted assignment label of the seawater exchange parameters in each monitoring area with each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the weighted assignment labels of the seawater exchange parameters in all monitoring areas as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weighted assignment of the seawater exchange parameters in each monitoring area is determined according to the model output results, and the overall protection performance coefficient is calculated after the weighted average calculation of the weighted assignment labels of the seawater exchange parameters in each monitoring area.

3. The seawater exchange breakwater protection performance evaluation system according to claim 2, characterized in that: The obtained overall protection performance coefficient is compared with the reference threshold of the overall protection performance. If the overall protection performance coefficient is greater than or equal to the reference threshold of the overall protection performance, it is classified as normal protection and no immediate measures are needed; if the overall protection performance coefficient is less than the reference threshold of the overall protection performance, it is classified as abnormal protection and further investigation of the cause is required and corresponding improvement measures should be taken.

4. Seawater exchange breakwater disaster early warning system, characterized by: Including data acquisition module, data analysis module, energy reduction analysis module and risk prediction module: Data acquisition module: divides the breakwater into several monitoring areas, obtains the seawater exchange parameters in different time periods in each monitoring area, and sends the obtained seawater exchange parameters to the data analysis module; Data analysis module: classify according to the type of seawater exchange parameters, identify and analyze the changing trends of seawater flow rate and water quality, determine the weighted values ​​of seawater exchange parameters in the monitoring area, and calculate the overall protection performance coefficient of the breakwater by weighted average based on the weighted values ​​of seawater exchange parameters in each monitoring area; the seawater exchange parameters include the seawater flow rate anomaly index and the water quality parameter deviation value; Specifically, the seawater exchange parameters include analyzing the change trend of the seawater flow rate data to obtain the seawater flow rate anomaly index. The method for obtaining the seawater flow rate anomaly index is as follows: Obtain seawater velocity data within time period t, standardize the acquired seawater velocity data, and construct a time series of seawater velocity data , decompose the time series Yt into trend component Tt, seasonal component St and residual component Rt, extract the decomposed residual component Rt, and use it to identify abnormal seawater velocity data. Calculate the mean μR and standard deviation σR of the residual component, obtain the standard threshold λ of seawater velocity under standard conditions, and identify and analyze abnormal seawater data. ,but For abnormal seawater data, the abnormal seawater data is analyzed and the seawater velocity abnormality index is calculated. The specific calculation expression is: ; Where LK is the abnormal seawater velocity index; Analyze the changing trend of water quality parameters and obtain the deviation value of water quality parameters. The method for obtaining the deviation value of water quality parameters is as follows: preprocess the water quality parameters obtained in real time, where the water quality parameters specifically include dissolved oxygen, pH value, conductivity and salinity; select the isolation forest algorithm, prepare a training data set, including all preprocessed water quality parameter time series data, use the isolation forest algorithm to train the model, learn the normal water quality parameter data pattern, define the number of trees in the forest, and the number of samples used to train each tree. Use the trained isolation forest model to calculate the anomaly score of each data point. The specific model calculation expression is: ; In the formula, is the path length of the i-th tree to the data point X, n is the number of trees in the forest, i is the tree number, The abnormal score of each data point is used to calculate the water quality parameter deviation value. The specific calculation expression is: ; Where DV is the water quality parameter deviation value, is the anomaly score at time m; Energy reduction analysis module: real-time monitoring and measurement of incident and transmitted wave energy, to determine the change in the reduction of wave energy by the breakwater; The energy reduction analysis module specifically includes: continuously monitoring the height and energy of waves through a wave height sensor, calculating the wave energy at each moment through incident wave and transmitted wave data at each time point, analyzing the stability of wave energy at each time point, and obtaining the wave energy stability value. The method for obtaining the wave energy stability value is: The wave energy at each moment is calculated through the incident wave and transmitted wave data at each time point. The specific calculation expression is: ; In the formula, is the wave energy at each moment, ρ is the water density, g is the gravitational acceleration, and H is the wave height; Set the time window size to w, determine the number of time points included in each calculation of the wave energy stability value, calculate the wave energy average μt in each window, and for each time point t, calculate the wave energy average in the window [t−w+1,t]; and the wave energy standard deviation σt in the window [t−w+1,t]; calculate the wave energy stability value based on the calculated wave energy average and standard deviation in each window. The specific calculation expression is: ; Where AQ is the stable value of wave energy; Risk prediction module: Based on the changes in the overall protection performance coefficient and wave energy reduction, disaster risk prediction and early warning are carried out by using fuzzy logic.

5. The seawater exchange breakwater disaster warning system according to claim 4 is characterized in that: The overall protection performance coefficient and wave energy stability value are used as input items, and the disaster warning level is used as output item; Define fuzzy sets for overall protection performance coefficient and wave energy stability value, and define fuzzy sets for disaster risk; Establish fuzzy rules and use fuzzy reasoning methods to determine the disaster risk level; The specific numerical value is fuzzified, the fuzzy rules are input for reasoning, and the fuzzy reasoning results are defuzzified to obtain the specific risk level.

6. The seawater exchange breakwater disaster warning system according to claim 5 is characterized by: When the risk level is high, a level one warning signal is generated and the emergency response mechanism is activated; when the risk level is medium, a level two warning signal is generated and monitoring is strengthened; when the risk level is low, a level three warning signal is generated and routine maintenance is carried out.

Images