Safety monitoring and early warning system of floating breakwater structure based on multi-source data

Abstract

The present invention discloses a floating breakwater structure safety monitoring and early warning system based on multi-source data, and relates to the field of floating breakwater safety monitoring. By obtaining the overall strength design value and each node strength design value of the floating breakwater to be monitored, setting the maximum load bearing value of the node and the maximum load bearing value of the structure as a whole as the early warning threshold, formulating an early warning strategy, constructing a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, outputting the mapping relationship between the wave characteristic parameters and the node load values, calculating the load values ​​of each node, performing finite element analysis on the structure of the floating breakwater, and calculating the overall load value of the floating breakwater under the influence of the wave characteristic parameters according to the acquired stress node load values, judging whether the acquired overall load value and stress node load value of the floating breakwater trigger the early warning strategy, and performing an alarm action when the early warning strategy is triggered.

Description

Technical Field

[0001] The invention relates to the field of floating breakwater safety monitoring, and in particular to a floating breakwater structure safety monitoring and early warning system based on multi-source data. Background Art

[0002] The long-term erosion and damage of seawalls, reefs and marine life near the coast in the ocean will cause great economic losses. Therefore, it is particularly important to build breakwaters near the coast. As a new type of marine wave-resistant technology, floating breakwater structures include pontoon type, raft type, pontoon type, membrane type and plate net type. The principle is to reflect part of the energy of the incident wave through its own movement and consume a large amount of wave energy by doing work on the waves, providing a relatively stable sea condition for the dock, improving the operation efficiency of the port and ensuring the safety of personnel. At the same time, it prevents the silt and sand swept in by waves and currents from accumulating in the port and reducing the dredging operation. In waters prone to icing, floating breakwaters can also effectively block ice from entering the port, thereby reducing the adverse effects on the port. The energy absorbed by the breakwater can be converted into electrical energy through a power generation device. Floating breakwaters have the advantages of low cost, fast transportation, easy installation, less environmental damage, and less damage to seabed resources. Therefore, they have great economic benefits and high application prospects.

[0003] The structural safety of floating breakwaters mainly includes: the safety of the main structure of floating breakwaters (main body, local strength and fatigue), the safety of mooring system (evaluation of node tension, mooring points and mooring cable strength), and the safety of connecting structures. The safety of the main structure is mainly affected by environmental loads, overall strength and node strength. In actual application, the overall strength and node strength of the breakwater are fixed values, so its structural safety depends on the environmental loads it receives during operation. The loads received by floating breakwaters in waves are closely related to the draft of the breakwater, the wave height, phase, period and wave angle of the wave. However, in the actual working process of the breakwater, due to the complexity of the marine environment, the factors affecting the breakwater often appear randomly and freely combined. Therefore, it is difficult to calculate the environmental loads effectively and timely. To this end, we propose a floating breakwater structural safety monitoring and early warning system based on multi-source data. Summary of the invention

[0004] The main purpose of the present invention is to provide a floating breakwater structure safety monitoring and early warning system based on multi-source data, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] The floating breakwater structure safety monitoring and early warning system based on multi-source data includes wave parameter acquisition module, node load acquisition module, neural network construction module, overall load acquisition module, early warning strategy formulation module, and safety monitoring and control module;

[0007] The load parameter acquisition module is used to collect wave characteristic parameters that affect the size of the environmental load on the floating breakwater, wherein the wave characteristic parameters include at least one of the draft value of the breakwater, the wave height, phase, period, and wave direction angle of the wave;

[0008] The node load acquisition module is used to collect node load values ​​of stress nodes of the floating breakwater under the influence of the wave characteristic parameters;

[0009] The neural network construction module is used to construct a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and output the mapping relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model. i →Fn j , where x i Expressed as the i-th wave characteristic parameter value, Fn j It is expressed as the j-th node load value, the neural network model is a BP neural network model of input layer-hidden layer-output layer structure, and the number of neurons in the input layer of the BP neural network model is equal to the number of types of the wave characteristic parameters, the number of neurons in the output layer is equal to the number of output data types, and the number of neurons in the hidden layer is determined according to the following formula, specifically:

[0010]

[0011] Where s is the number of neurons in the hidden layer; m is the number of neurons in the input layer; n is the number of neurons in the output layer; a is an integer, and the value range of a is [1,9]; Expressed as a pair The values ​​in are rounded up;

[0012] The overall load acquisition module performs finite element analysis on the structure of the floating breakwater, and calculates the overall load value of the floating breakwater under the influence of the wave characteristic parameters according to the acquired stress node load values;

[0013] The early warning strategy formulation module is used to formulate an early warning strategy according to the overall strength and node strength of the floating breakwater and the overall load value and stress node load value of the floating breakwater under the influence of the wave characteristic parameters obtained by calculation, and the formulation steps include:

[0014] Obtain the overall strength design value Ft and each node strength design value Fs of the floating breakwater to be monitoredj , Fs j It is expressed as the design value of the strength of the jth node;

[0015] The importance of a node is calculated based on its degree centrality. The calculation formula is:

[0016] NI j =αd 1j +βd 2j

[0017] Where NI j It is represented as the importance evaluation value of the jth node; d 1j It is represented by the number of nodes connected in series by the jth node in the entire floating breakwater structure; d 2j It is represented by the number of nodes connected in parallel by the jth node in the entire floating breakwater structure; α and β are constant coefficients, and α+β=1, α>β;

[0018] Using the node importance evaluation value NI j Create a sample set, denoted as {NI1, NI2,,,,NI j}, get the mean and standard deviation of the sample set, and use the mean and standard deviation to standardize the data. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data;

[0019] After standardization is completed, the standard parameters are used Adjust the numerical interval to [0,1], and use the function value of f(k) to classify the importance evaluation values ​​of the nodes. The classification mechanism is:

[0020] When f(k) min When ≤f(k)<f(k)1, the importance evaluation value of the node is classified as level one;

[0021] When f(k)1≤f(k)<f(k)2, the importance evaluation value of the node is classified as level 2;

[0022] When f(k)2≤f(k)<f(k) max When , the importance evaluation value of the node is classified into three levels;

[0023] Among them, f(k) min ,f(k) max are the minimum and maximum values ​​of the function value of f(k), f(k)1 and f(k)2 are the middle values ​​of f(k), and f(k) min <f(k)1<f(k)2<<f(k) max ;

[0024] Set the maximum load value Fn of the jth node according to the importance of the node jmax And the maximum load value Ft of the structure as a whole max , the maximum load value of the node Fn jmax The specific setting principles are:

[0025] When the importance evaluation value of a node is classified as level 1, its maximum load value Fn jmax ≤(0.8-0.9)Fs j ;

[0026] When the importance evaluation value of a node is classified as level 2, its maximum load value Fn jmax ≤(0.75-0.85)Fs j ;

[0027] When the importance evaluation value of the node is classified as level three, its maximum load value Fn jmax ≤(0.7-0.8)Fs j ;

[0028] The maximum load value Ft of the entire structure max The setting principle is: Ft max ≤0.95Ft;

[0029] The maximum load bearing value of the set node and the maximum load bearing value of the entire structure are used as warning thresholds;

[0030] The safety monitoring control module is used to perform an alarm action when the overall load value and the stress node load value of the floating breakwater trigger the early warning strategy.

[0031] The system workflow includes the following steps:

[0032] Obtain the overall strength design value Ft and each node strength design value Fs of the floating breakwater to be monitored j ;

[0033] The importance of the node is calculated according to the degree centrality of the node, and the maximum load value Fn of the jth node is set according to the node importance. jmax And the maximum load value Ft of the structure as a whole max ;

[0034] The maximum load bearing value of the set nodes and the maximum load bearing value of the entire structure are used as warning thresholds to formulate warning strategies;

[0035] Collecting historical data of wave characteristic parameters affecting the magnitude of environmental loads on the floating breakwater and node load values ​​of stress nodes of the floating breakwater under the influence of the wave characteristic parameters;

[0036] Construct a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and output the mapping relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model f:x i →Fn j ;

[0037] Obtain the real-time wave characteristic parameters that affect the size of the environmental load on the floating breakwater, and use the obtained mapping relationship f:x i →Fn j Calculate the load value of each node;

[0038] Performing finite element analysis on the structure of the floating breakwater, and calculating the overall load value of the floating breakwater under the influence of the wave characteristic parameters according to the obtained stress node load values;

[0039] It is determined whether the obtained overall load value and stress node load value of the floating breakwater trigger the early warning strategy, and an alarm action is performed when the early warning strategy is triggered.

[0040] The present invention has the following beneficial effects:

[0041] Compared with the prior art, the technical solution of the present invention obtains the overall strength design value and the strength design value of each node of the floating breakwater to be monitored, sets the maximum load-bearing value of the node and the maximum load-bearing value of the structure as a whole according to the importance of the node, takes the set maximum load-bearing value of the node and the maximum load-bearing value of the structure as a whole as the warning threshold, formulates a warning strategy, collects the wave characteristic parameters that affect the size of the environmental load on the floating breakwater and the historical data of the node load values ​​of the stress nodes of the floating breakwater under the influence of the wave characteristic parameters, constructs a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and outputs the relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model. The mapping relationship between the two is used to obtain the real-time wave characteristic parameters that affect the size of the environmental load on the floating breakwater, and the load value of each node is calculated according to the obtained mapping relationship. The finite element analysis of the structure of the floating breakwater is performed, and the overall load value of the floating breakwater under the influence of the wave characteristic parameters is calculated according to the obtained stress node load value. It is determined whether the obtained overall load value and stress node load value of the floating breakwater trigger the early warning strategy, and an alarm action is performed when the early warning strategy is triggered. Through the constructed neural network model, the environmental load under different combined working conditions of influencing factors can be obtained, so that the environmental load can be calculated in time according to the real-time wave characteristic parameters, so as to realize real-time monitoring and early warning of the safety of the main structure of the floating breakwater. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1It is a structural block diagram of the floating breakwater structure safety monitoring and early warning system based on multi-source data of the present invention;

[0043] Figure 2 The following is a schematic diagram of the system implementation process. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0045] Example 1

[0046] like Figure 1-2 As shown, the specific implementation process of the technical solution of the present invention includes the following steps:

[0047] Step 1: Obtain the overall strength design value Ft and each node strength design value Fs of the floating breakwater to be monitored j ;

[0048] Step 2: Calculate the importance of the node according to its degree centrality. The calculation formula is:

[0049] NI j =αd 1j +βd 2j

[0050] Where NI j It is represented as the importance evaluation value of the jth node; d 1j It is represented by the number of nodes connected in series by the jth node in the entire floating breakwater structure; d 2j It is expressed as the number of nodes connected in parallel by the jth node in the entire floating breakwater structure; α and β are constant coefficients, and α+β=1, α>β. The maximum load value Fn of the jth node is set according to the importance of the node. jmax And the maximum load value Ft of the structure as a whole max , the specific steps are:

[0051] S21: Using the node importance evaluation value NI j Create a sample set, denoted as {NI1, NI2,,,,NI j}, get the mean and standard deviation of the sample set, and use the mean and standard deviation to standardize the data. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data;

[0052] S22: After standardization is completed, the standard parameters are used Adjust the numerical interval to [0,1], and use the function value of f(k) to classify the importance evaluation values ​​of the nodes. The classification mechanism is:

[0053] When f(k) min When ≤f(k)<f(k)1, the importance evaluation value of the node is classified as level one;

[0054] When f(k)1≤f(k)<f(k)2, the importance evaluation value of the node is classified as level 2;

[0055] When f(k)2≤f(k)<f(k) max When , the importance evaluation value of the node is classified into three levels;

[0056] Among them, f(k) min ,f(k) max are the minimum and maximum values ​​of the function value of f(k), f(k)1 and f(k)2 are the middle values ​​of f(k), and f(k) min <f(k)1<f(k)2<<f(k) max ;

[0057] S23: Set the maximum load value Fn of the jth node according to the importance of the node jmax And the maximum load value Ft of the structure as a whole max , the maximum load value of the node Fn jmax The specific setting principles are:

[0058] When the importance evaluation value of a node is classified as level 1, its maximum load bearing value Fn jmax ≤(0.8-0.9)Fs j ;

[0059] When the importance evaluation value of a node is classified as level 2, its maximum load value Fn jmax ≤(0.75-0.85)Fs j ;

[0060] When the importance evaluation value of the node is classified as level three, its maximum load value Fn jmax ≤(0.7-0.8)Fs j ;

[0061] The maximum load value Ft of the entire structure max The setting principle is: Ft max ≤0.95Ft;

[0062] Step 3: Take the maximum load value of the node and the maximum load value of the structure as a whole as the warning threshold and formulate a warning strategy;

[0063] Step 4: Collect historical data of wave characteristic parameters that affect the size of environmental loads on the floating breakwater and node load values ​​of stress nodes of the floating breakwater under the influence of the wave characteristic parameters. In this embodiment, the wave characteristic parameters include the draft value of the breakwater, the wave height, phase, period, and wave direction angle of the wave;

[0064] Step 5: Construct a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and output the mapping relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model f:x i →Fn j , where x i Expressed as the i-th wave characteristic parameter value, Fn j It is expressed as the j-th node load value. The neural network model is a BP neural network model with an input layer-hidden layer-output layer structure. The number of neurons in the input layer of the BP neural network model is equal to the number of types of wave characteristic parameters, the number of neurons in the output layer is equal to the number of types of output data, and the number of neurons in the hidden layer is determined according to the following formula, specifically:

[0065]

[0066] Where s is the number of neurons in the hidden layer; m is the number of neurons in the input layer. In this model, m = 5; n is the number of neurons in the output layer. In this model, n = 1; a is an integer, and the value range of a is [1,9]. Expressed as a pair The value in is rounded up, and a=5, we have Then the neural network model is a BP neural network model with an input layer of 5 neurons, a hidden layer of 8 neurons, and an output layer of 1 neuron;

[0067] Step 6: Obtain the real-time wave characteristic parameters that affect the size of the environmental load on the floating breakwater, and use the obtained mapping relationship f:x i →Fn j Calculate the load value of each node;

[0068] Step 7: Perform finite element analysis on the structure of the floating breakwater, and calculate the overall load value of the floating breakwater under the influence of wave characteristic parameters based on the obtained stress node load values;

[0069] Step 8: Determine whether the obtained overall load value and stress node load value of the floating breakwater trigger the early warning strategy, and perform an alarm action when the early warning strategy is triggered.

[0070] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A floating breakwater structure safety monitoring and early warning system based on multi-source data, characterized in that: It includes wave parameter acquisition module, node load acquisition module, neural network construction module, overall load acquisition module, early warning strategy formulation module, and safety monitoring and control module; The load parameter acquisition module is used to collect wave characteristic parameters that affect the size of the environmental load on the floating breakwater; The node load acquisition module is used to collect node load values ​​of stress nodes of the floating breakwater under the influence of the wave characteristic parameters; The neural network construction module is used to construct a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and output the mapping relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model. i →Fn j , where x i Expressed as the i-th wave characteristic parameter value, Fn j Expressed as the j-th node load value; The overall load acquisition module performs finite element analysis on the structure of the floating breakwater, and calculates the overall load value of the floating breakwater under the influence of the wave characteristic parameters according to the acquired stress node load values; The early warning strategy formulation module is used to formulate an early warning strategy according to the overall strength and node strength of the floating breakwater and the overall load value and stress node load value of the floating breakwater under the influence of the wave characteristic parameters obtained by calculation; The safety monitoring control module is used to perform an alarm action when the overall load value and stress node load value of the floating breakwater trigger the early warning strategy; The steps to develop an early warning strategy include: Obtain the overall strength design value Ft and each node strength design value Fs of the floating breakwater to be monitored j , Fs j It is expressed as the design value of the strength of the jth node; The importance of a node is calculated based on its degree centrality. The calculation formula is: BY j =αd 1j +βd 2j Where NI j It is represented as the importance evaluation value of the jth node; d 1j It is represented by the number of nodes connected in series by the jth node in the entire floating breakwater structure; d 2j It is represented by the number of nodes connected in parallel by the jth node in the entire floating breakwater structure; α and β are constant coefficients, and α+β=1, α>β; Using the node importance evaluation value NI j Create a sample set, denoted as {NI1, NI2,,,,NI j }, get the mean and standard deviation of the sample set, and use the mean and standard deviation to standardize the data. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data; After standardization is completed, the standard parameters are used Adjust the numerical interval to [0,1], and use the function value of f(k) to classify the importance evaluation values ​​of the nodes. The classification mechanism is: When f(k) min When ≤f(k)<f(k)1, the importance evaluation value of the node is classified as level one; When f(k)1≤f(k)<f(k)2, the importance evaluation value of the node is classified as level 2; When f(k)2≤f(k)<f(k) max When , the importance evaluation value of the node is classified into three levels; Among them, f(k) min ,f(k) max are the minimum and maximum values ​​of the function value of f(k), f(k)1 and f(k)2 are the middle values ​​of f(k), and f(k) min <f(k)1<f(k)2<<f(k) max ; Set the maximum load value Fn of the jth node according to the importance of the node jmax And the maximum load value Ft of the structure as a whole max ; The maximum load-bearing value of the set node and the maximum load-bearing value of the entire structure are used as warning thresholds.

2. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 1 is characterized by: The wave characteristic parameters include at least one of the draft value of the breakwater, the wave height, phase, period, and wave direction angle of the wave.

3. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 1 is characterized by: The neural network model is a BP neural network model with an input layer-hidden layer-output layer structure, and the number of neurons in the input layer of the BP neural network model is equal to the number of types of the wave characteristic parameters, and the number of neurons in the output layer is equal to the number of types of output data.

4. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 3 is characterized by: The number of neurons in the hidden layer is determined according to the following formula, specifically: Where s is the number of neurons in the hidden layer; m is the number of neurons in the input layer; n is the number of neurons in the output layer; a is an integer, and the value range of a is [1,9]; Expressed as a pair The values ​​in are rounded up.

5. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 1 is characterized by: The maximum load value of the node Fn jmax The specific setting principles are: When the importance evaluation value of a node is classified as level 1, its maximum load value Fn jmax ≤(0.8-0.9)Fs j ; When the importance evaluation value of a node is classified as level 2, its maximum load value Fn jmax ≤(0.75-0.85)Fs j ; When the importance evaluation value of the node is classified as level three, its maximum load value Fn jmax ≤(0.7-0.8)Fs j .

6. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 1 is characterized by: The maximum load value Ft of the entire structure max The setting principle is: Ft max ≤0.95Ft.

7. The floating breakwater structure safety monitoring and early warning system based on multi-source data according to claim 1 is characterized by: The workflow of the system includes the following steps: Obtain the overall strength design value Ft and each node strength design value Fs of the floating breakwater to be monitored j ; The importance of the node is calculated according to the degree centrality of the node, and the maximum load value Fn of the jth node is set according to the node importance. jmax And the maximum load value Ft of the structure as a whole max ; The maximum load bearing value of the set nodes and the maximum load bearing value of the entire structure are used as warning thresholds to formulate warning strategies; Collecting historical data of wave characteristic parameters affecting the magnitude of environmental loads on the floating breakwater and node load values ​​of stress nodes of the floating breakwater under the influence of the wave characteristic parameters; Construct a neural network model with the acquired wave characteristic parameters as output and the acquired node load values ​​as output, and output the mapping relationship between the wave characteristic parameters and the node load values ​​according to the constructed network model f:x i →Fn j ; Obtain the real-time wave characteristic parameters that affect the size of the environmental load on the floating breakwater, and use the obtained mapping relationship f:x i →Fn j Calculate the load value of each node; Performing finite element analysis on the structure of the floating breakwater, and calculating the overall load value of the floating breakwater under the influence of the wave characteristic parameters according to the obtained stress node load values; It is determined whether the obtained overall load value and stress node load value of the floating breakwater trigger the early warning strategy, and an alarm action is performed when the early warning strategy is triggered.

Images