A method and system for indirectly monitoring ship outboard water pressure load

Abstract

The present invention belongs to the field of ship technology. A method and system for indirect monitoring of the ship's outboard water pressure load is provided. The method comprises: establishing a finite element model for accurately describing the structural characteristics and mechanical response of the target hull, and establishing a CFD model of the target hull; calculating the outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix according to the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and the structural response data based on the influence coefficient matrix; receiving the structural response data measured by sensors arranged at the best measuring points on the hull, and inverting the structural response data and the relationship to obtain the real-time outboard water pressure load. The present invention adopts an indirect measurement method to monitor the outboard water pressure load of the ship in real time, overcoming the limitations of the direct monitoring method of damaging the hull and the large number of sensors arranged.

Description

Technical Field

[0001] The present invention relates to the technical field of ships, and in particular to a method and system for indirectly monitoring the outboard water pressure load of a ship. Background Art

[0002] The outboard water pressure load refers to the pressure from the outboard water on the hull (side structure) of a ship when it is sailing or anchored in the water. The load formed by this pressure has a significant impact on the strength and stability of the hull structure.

[0003] Currently, methods for determining outboard hydraulic loads and their distribution primarily rely on standardized methods based on experience and simplified formulas, as well as simulation calculations based on fluid dynamics theory. However, both methods have limitations and fail to truly reflect the loads experienced by ships during actual use. Directly measuring outboard hydraulic loads, such as using pressure sensors, while theoretically feasible, faces numerous challenges in practical application. For example, the sensors require drilling holes into the structure for installation, which can affect structural strength. Furthermore, for large structures like the hull, deploying a large number of pressure sensors is not only costly but also difficult to achieve comprehensive coverage.

[0004] It can be seen that how to efficiently and accurately monitor the ship's outboard water pressure load without damaging the hull's structural strength is a technical problem that needs to be solved. Summary of the Invention

[0005] To this end, the present invention provides a method, system, electronic equipment, computer storage medium and computer program product for indirect monitoring of the outboard water pressure load of a ship to solve the above technical problems.

[0006] The present invention discloses a method for indirectly monitoring the outboard water pressure load of a ship, the method comprising the following steps:

[0007] Establish a finite element model to accurately describe the structural characteristics and mechanical response of the target hull, and establish a CFD model of the target hull;

[0008] Calculating an outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix based on the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and structural response data based on the influence coefficient matrix;

[0009] Structural response data measured by sensors arranged at optimal measuring points on the hull are received, and a real-time outboard water pressure load is obtained based on the structural response data and the relational expression.

[0010] Optionally, the influence coefficient matrix is ​​as follows:

[0011]

[0012] Where C is the influence coefficient matrix, n is the number of measuring points, m is the number of unit loads, and element c is mn It represents the structural response coefficient of the nth best measuring point under the unit load m;

[0013] The relationship between the outboard water pressure load and the structural response data is as follows:

[0014] R=C·F

[0015] Wherein, R is the structural response vector measured by the sensors at each of the optimal measuring points, and F is the real-time outboard water pressure load to be inverted.

[0016] Optionally, the deriving of a real-time outboard water pressure load based on the structural response data and the inversion relationship includes:

[0017] F=(C T C -1 C T R

[0018] Where C T is the transposed matrix of the influence coefficient matrix C, (C T C) -1 C T is the pseudo-inverse matrix.

[0019] Optionally, the method further includes:

[0020] The CFD model is used to calculate the water pressure distribution information on the outer surface of the hull under different sea conditions, and a multidimensional function approximation algorithm is used to fit the water pressure distribution information to obtain a unified mathematical expression of the water pressure load on the entire ship. The unified mathematical expression is used as a unit load to input into the finite element model to obtain a full-field strain result;

[0021] According to the full-field strain results, the sensor layout is optimized using an intelligent optimization algorithm to obtain layout information of the optimal measuring points, wherein the layout information includes the optimal measuring point position and the optimal measuring point direction;

[0022] An influence coefficient matrix is ​​constructed using the optimized sensor layout information.

[0023] In some embodiments, the use of an intelligent optimization algorithm to optimize the sensor layout to obtain optimal measurement point layout information includes:

[0024] Analyzing and processing the full-field strain results using a convolutional neural network-based sensor layout optimization model to obtain a plurality of target deployment areas and corresponding optimal measurement point directions, and selecting a first number of optimal measurement point positions in each of the target deployment areas; wherein the target deployment areas are areas on the outer surface of the target vessel that are sensitive to structural response;

[0025] The sensor layout optimization model also outputs a number of predicted non-target deployment areas and corresponding optimal measurement point directions, and selects a second number of the optimal measurement point positions in each of the non-target deployment areas; wherein the non-target deployment areas are located within a preset distance around the target deployment area.

[0026] The present invention also provides an indirect monitoring system for outboard water pressure loads on a ship, the system comprising a plurality of sensors, a processor, and a memory; the processor calls a computer program code in the memory to execute the following steps:

[0027] Establish a finite element model to accurately describe the structural characteristics and mechanical response of the target hull, and establish a CFD model of the target hull;

[0028] Calculating an outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix based on the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and structural response data based on the influence coefficient matrix;

[0029] Structural response data measured by sensors arranged at optimal measuring points on the hull are received, and a real-time outboard water pressure load is obtained based on the structural response data and the relational expression.

[0030] Optionally, the influence coefficient matrix is ​​as follows:

[0031]

[0032] Where C is the influence coefficient matrix, n is the number of measuring points, m is the number of unit loads, and element c is mn It represents the structural response coefficient of the nth best measuring point under the unit load m;

[0033] The relationship between the outboard water pressure load and the structural response data is as follows:

[0034] R=C·F

[0035] Wherein, R is the structural response vector measured by the sensors at each of the optimal measuring points, and F is the real-time outboard water pressure load to be inverted.

[0036] Optionally, the deriving of a real-time outboard water pressure load based on the structural response data and the inversion relationship includes:

[0037] F=(C T C) -1 C T R

[0038] Where C T is the transposed matrix of the influence coefficient matrix C, (C T C) -1 C T is the pseudo-inverse matrix.

[0039] Optionally, it also includes:

[0040] The CFD model is used to calculate the water pressure distribution information on the outer surface of the hull under different sea conditions, and a multidimensional function approximation algorithm is used to fit the water pressure distribution information to obtain a unified mathematical expression of the water pressure load on the entire ship. The unified mathematical expression is used as a unit load to input into the finite element model to obtain a full-field strain result;

[0041] According to the full-field strain results, the sensor layout is optimized using an intelligent optimization algorithm to obtain layout information of the optimal measuring points, wherein the layout information includes the optimal measuring point position and the optimal measuring point direction;

[0042] An influence coefficient matrix is ​​constructed using the optimized sensor layout information.

[0043] In some embodiments, the use of an intelligent optimization algorithm to optimize the sensor layout to obtain optimal measurement point layout information includes:

[0044] Analyzing and processing the full-field strain results using a convolutional neural network-based sensor layout optimization model to obtain a plurality of target deployment areas and corresponding optimal measurement point directions, and selecting a first number of optimal measurement point positions in each of the target deployment areas; wherein the target deployment areas are areas on the outer surface of the target vessel that are sensitive to structural response;

[0045] The sensor layout optimization model also outputs a number of predicted non-target deployment areas and corresponding optimal measurement point directions, and selects a second number of the optimal measurement point positions in each of the non-target deployment areas; wherein the non-target deployment areas are located within a preset distance around the target deployment area.

[0046] The present invention also discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and runnable on the at least one processor, wherein the computer program code implements the method described in any of the preceding items when executed.

[0047] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program code is executed, the method as described in any of the above items is implemented.

[0048] The present invention also discloses a computer program product. The computer program product is pre-packaged with computer program code. When the computer program code is executed, the method described in any of the above items is implemented.

[0049] The present invention has the following beneficial effects: Based on a load identification algorithm, the present invention integrates fluid simulation, structural simulation, and physical measurement technologies to form a comprehensive indirect measurement method for a ship's outboard hydraulic loads by establishing a linear mapping relationship between the outboard hydraulic loads and the ship's structural response data. This indirect measurement method overcomes the limitations of the direct monitoring methods mentioned in the background art and enables real-time monitoring of a ship's outboard hydraulic loads. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a flow chart of a method for indirectly monitoring the outboard water pressure load of a ship disclosed in an embodiment of the present invention;

[0052] Figure 2 This is another overall flow chart of a method for indirectly monitoring the outboard water pressure load of a ship disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0055] Directly measuring the outboard water pressure load, such as using pressure sensors, is theoretically feasible, but faces many challenges in practical applications. For example, the sensors need to be installed through holes in the structure, which will affect the structural strength. At the same time, for large structures such as the hull, deploying a large number of pressure sensors is not only costly but also difficult to achieve full coverage. It can be seen that how to efficiently and accurately monitor the outboard water pressure load of a ship without damaging the structural strength of the hull is a technical problem that needs to be solved.

[0056] In response to the above technical issues, such as Figure 1 、 Figure 2 As shown, an embodiment of the present invention discloses a method for indirectly monitoring the outboard water pressure load of a ship, the method comprising the following steps:

[0057] S10, establishing a finite element model for accurately describing the structural characteristics and mechanical response of the target hull, and establishing a CFD model of the target hull.

[0058] S20, calculating the outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix according to the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and the structural response data based on the influence coefficient matrix.

[0059] S30, receiving structural response data measured by sensors arranged at optimal measuring points on the hull, and deriving a real-time outboard water pressure load based on the structural response data and the relationship.

[0060] Based on a load identification algorithm, this invention integrates fluid simulation, structural simulation, and physical measurement techniques to form a comprehensive indirect measurement method for a ship's outboard hydraulic loads. This method establishes a linear mapping relationship between the outboard hydraulic loads and the ship's structural response data. This indirect measurement method overcomes the limitations of the direct monitoring methods mentioned in the background art and enables real-time monitoring of a ship's outboard hydraulic loads.

[0061] In addition, after the real-time outboard water pressure load of the target ship is obtained by inversion, the real-time outboard water pressure load can be displayed intuitively so that relevant personnel can evaluate the stress condition of the hull at any time during the navigation of the ship and improve navigation safety.

[0062] Optionally, the influence coefficient matrix is ​​as follows:

[0063]

[0064] Where C is the influence coefficient matrix, n is the number of measuring points, m is the number of unit loads, and element c is mn It represents the structural response coefficient of the nth best measuring point under the unit load m;

[0065] The relationship between the outboard water pressure load and the structural response data is as follows:

[0066] R=C·F

[0067] Wherein, R is the structural response vector measured by the sensors at each of the optimal measuring points, and F is the real-time outboard water pressure load to be inverted.

[0068] In embodiments of the present invention, theoretical calculation formulas for a ship's outboard hydraulic load are often listed separately according to pressure components or locations of action, resulting in complex and computationally difficult formulas. A method that can uniformly express the global hydraulic load using a single general formula has yet to be found. The present invention, through a unified and simple approach, achieves an approximate expression of a ship's outboard hydraulic load and its distribution at any moment under varying environmental conditions. Based on the pressure results of numerical tank tests, the present invention explores the ability of various multidimensional function approximation methods to reconstruct the ship's outboard hydraulic load field. Using appropriate basis functions and parameter identification methods, a unified approximate expression for the ship's outboard hydraulic load is constructed based on a spatial three-dimensional approximation function.

[0069] Optionally, the deriving of a real-time outboard water pressure load based on the structural response data and the inversion relationship includes:

[0070] F=(C T C) -1 C T R

[0071] Where C T is the transposed matrix of the influence coefficient matrix C, (C T C) -1 C T is the pseudo-inverse matrix.

[0072] Optionally, the method further includes:

[0073] The CFD model is used to calculate the water pressure distribution information on the outer surface of the hull under different sea conditions, and a multidimensional function approximation algorithm is used to fit the water pressure distribution information to obtain a unified mathematical expression of the water pressure load on the entire ship. The unified mathematical expression is used as a unit load to input into the finite element model to obtain a full-field strain result;

[0074] According to the full-field strain results, the sensor layout is optimized using an intelligent optimization algorithm to obtain layout information of the optimal measuring points, wherein the layout information includes the optimal measuring point position and the optimal measuring point direction;

[0075] An influence coefficient matrix is ​​constructed using the optimized sensor layout information.

[0076] In an embodiment of the present invention, the present invention applies the influence coefficient method to identify the outboard water pressure load of a ship. Different from the previous method based on the division of structural load-bearing units, the above-mentioned mathematical model of the unit load function based on global distribution is established, and the uncertainty of load identification is taken into account. By studying the layout optimization of multiple types of sensors, the pathological nature of the influence coefficient matrix is ​​reduced.

[0077] Computational fluid dynamics (CFD) is a computer-based simulation technology that simulates a ship's interaction with water under varying sea conditions by solving fundamental equations of fluid dynamics, such as the Navier-Stokes equations. It accounts for multiple factors, including waves, currents, and ship motion, to calculate the water pressure distribution on the hull's outer surface. This water pressure distribution is discrete and distributed across various locations on the hull's outer surface, reflecting the external water pressure conditions at different locations on the ship. For example, when a ship is sailing, the bow experiences higher pressure due to the impact of the current, while the pressure distribution at the sides and stern varies due to factors such as the flow and vortices of the current. Different sea conditions, including varying wave heights, wavelengths, wave directions, current velocities, current directions, and wind conditions, all influence the water pressure distribution on the hull's outer surface. CFD models are capable of calculating these complex sea conditions, providing a rich data foundation for subsequent analysis.

[0078] Because the water pressure distribution information obtained by CFD calculations is discrete, it is difficult to directly use for subsequent structural analysis. The present invention uses multidimensional function approximation algorithms (such as polynomial function approximation and spline function approximation) to fit this discrete water pressure distribution information and express it as a unified mathematical expression. This mathematical expression can continuously describe the water pressure load on the entire outer surface of the hull, forming a unified mathematical expression for the water pressure load on the entire ship. This unified expression makes the description of the water pressure load more concise and accurate, facilitating subsequent use as an input parameter.

[0079] The finite element model is a numerical calculation method that divides a complex structure into multiple simple units. By inputting a unified mathematical expression of the entire ship's outboard water pressure load as a unit load (a total of m units), the finite element model simulates the mechanical response of the hull under the action of this water pressure load, and thus derives the aforementioned influence coefficient matrix. Each unit will produce corresponding strains and stresses under the action of the water pressure load, depending on its material properties and geometry. Through finite element calculations, the full-field strain results can be obtained, that is, the strain distribution of the entire hull structure under a given water pressure load. This strain distribution can reflect the degree of deformation and stress concentration areas of the hull structure at different locations, providing a basis for evaluating the strength and stability of the ship structure.

[0080] According to the full-field strain results, the sensor layout is optimized using intelligent optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) to make the sensor layout more scientific and reasonable. The full-field strain results need to be considered in the optimization process to find the best measuring point position and direction that can most accurately reflect the key response signals of the hull structure. For example, sensors are arranged in areas where the strain changes drastically, or in key positions that can reflect the overall deformation trend of the structure, so as to ensure that the mechanical response information of the hull structure under different working conditions is captured to the greatest extent with the least number of sensors. In addition, the determination of the optimal measuring point position and direction also needs to balance multiple factors such as monitoring effect and cost. For example, avoid placing sensors in areas that are insensitive to structural response, or avoid increasing costs and system complexity due to overly dense sensor layout.

[0081] Using the optimized sensor placement information, an influence coefficient matrix is ​​constructed. This influence coefficient matrix reflects the mapping relationship between the hull structural response data (i.e., the strain data measured by the sensors) and the real-time outboard hydraulic pressure load. Specifically, the elements in the influence coefficient matrix describe the strain changes at different sensor locations for each unit hydraulic pressure load change. This matrix allows the relationship between the strain signals measured by the sensors and the outboard hydraulic pressure load to be inferred, providing the mathematical foundation for subsequent load inversion.

[0082] In some embodiments, the use of an intelligent optimization algorithm to optimize the sensor layout to obtain optimal measurement point layout information includes:

[0083] Analyzing and processing the full-field strain results using a convolutional neural network-based sensor layout optimization model to obtain a plurality of target deployment areas and corresponding optimal measurement point directions, and selecting a first number of optimal measurement point positions in each of the target deployment areas; wherein the target deployment areas are areas on the outer surface of the target vessel that are sensitive to structural response;

[0084] The sensor layout optimization model also outputs a number of predicted non-target deployment areas and corresponding optimal measurement point directions, and selects a second number of the optimal measurement point positions in each of the non-target deployment areas; wherein the non-target deployment areas are located within a preset distance around the target deployment area.

[0085] In an embodiment of the present invention, in addition to the aforementioned intelligent optimization algorithms such as genetic algorithms and particle swarm optimization algorithms, the present invention can also use a sensor layout optimization model based on a convolutional neural network to analyze and process the full-field strain results. Convolutional neural network is a deep learning model that has outstanding performance in the fields of image recognition and data feature extraction. The present invention regards the full-field strain results as a "data image", which contains the strain information of the hull structure at different positions. Through its convolutional layer, pooling layer and fully connected layer, CNN can automatically extract complex features in the full-field strain results, including gradient changes in strain, local strain concentration areas, strain distribution patterns, etc., which helps to find areas that are sensitive to structural response, namely target layout areas, and non-target layout areas that are insensitive to structural response and are located within a preset distance around the target layout area.

[0086] The target deployment areas mentioned above refer to areas on the target vessel's hull surface that are sensitive to structural response, are more susceptible to outboard water pressure loads, and may be high-risk areas for structural failure. For example, areas such as the bow and stern of a ship, near the keel, and at structural joints are often sensitive to structural response due to their unique structure and stress conditions. By analyzing the full-field strain results using a CNN, these areas sensitive to structural response can be automatically identified. The model can divide the hull's outer surface into different areas based on factors such as the degree of strain concentration, the severity of strain changes, and the strain distribution pattern, and determine which areas are target deployment areas.

[0087] For each target placement area, the sensor placement optimization model also outputs the corresponding optimal measurement point orientation. This optimal measurement point orientation takes into account the force and strain directions of the structure within that area. For example, in a section of the structure subject to longitudinal tension, the optimal sensor measurement point orientation may be along the force direction to most effectively capture the strain signal. This helps improve sensor measurement accuracy and sensitivity, ensuring that the most critical structural response information in that area is monitored.

[0088] After the target deployment areas are determined, a first number of optimal measurement point locations are selected within each target deployment area. This number can be determined based on actual circumstances. For example, if the target deployment area is structurally more critical, more sensors can be installed there to ensure effective monitoring of key areas and timely detection of potential structural damage or failure risks. The optimal measurement point orientations for each optimal measurement point location within each target deployment area are consistent.

[0089] The above-mentioned full-field strain results may be abnormally high or low in some parts, for example, when the water pressure distribution information calculated by the aforementioned CFD model is locally inaccurate. Therefore, in addition to the target deployment area, the sensor layout optimization model of the present invention will also output a number of predicted non-target deployment areas and the corresponding optimal measurement point directions. At the same time, the non-target deployment area is an area not far from the target deployment area, that is, within a preset distance. In this way, the structural response data measured by the sensors in the adjacent area can be used to analyze and obtain a more accurate real-time outboard water pressure load. Among them, the second number in the non-target deployment area should be smaller than the first number in the target deployment area, for example, the first number is 6-10, and the second number is 2-5.

[0090] The sensor placement optimization model can include two sub-models: one sub-model analyzes and processes full-field strain data to determine target placement areas and their corresponding optimal measurement point directions; the other sub-model analyzes and processes full-field strain data to determine non-target placement areas and their corresponding optimal measurement point directions. The specific internal structure and training process of the sensor placement optimization model can be based on existing methods and will not be further described in detail in this disclosure.

[0091] An embodiment of the present invention further discloses an indirect monitoring system for outboard water pressure loads on a ship, the system comprising a plurality of sensors, a processor, and a memory; the processor calls computer program code in the memory to perform the following steps:

[0092] Establish a finite element model to accurately describe the structural characteristics and mechanical response of the target hull, and establish a CFD model of the target hull;

[0093] Calculating an outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix based on the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and structural response data based on the influence coefficient matrix;

[0094] Structural response data measured by sensors arranged at optimal measuring points on the hull are received, and a real-time outboard water pressure load is obtained based on the structural response data and the relational expression.

[0095] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program code implements the method described in any of the preceding items when executed.

[0096] An embodiment of the present invention further discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program code is executed, the method as described in any of the above items is implemented.

[0097] An embodiment of the present invention further discloses a computer program product. The computer program product is pre-packaged with computer program code, and when the computer program code is executed, the method as described in any of the above items is implemented.

[0098] The device embodiments described above are merely illustrative, and the modules designed therein may or may not be physically separate, i.e., they may be located in one place or distributed in multiple locations. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0099] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0100] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for indirectly monitoring the outboard water pressure load of a ship, characterized in that: The method comprises the following steps: Establish a finite element model to accurately describe the structural characteristics and mechanical response of the target hull, and establish a CFD model of the target hull; Calculating an outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix based on the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and structural response data based on the influence coefficient matrix; receiving structural response data measured by sensors arranged at optimal measuring points on the hull, and deriving a real-time outboard water pressure load based on the structural response data and the relationship; The influence coefficient matrix is ​​as follows: Where, is the influence coefficient matrix, n is the number of measuring points, m is the number of unit loads, and the elements It represents the structural response coefficient of the nth best measuring point under the unit load m; The relationship between the outboard water pressure load and the structural response data is as follows: Where, is the structural response vector measured by the sensor at each optimal measurement point, is the real-time outboard water pressure load to be inverted; The real-time outboard water pressure load is obtained based on the structural response data and the inversion relationship, including: Where, is the influence coefficient matrix The transposed matrix of is the pseudo-inverse matrix; The method further comprises: The CFD model is used to calculate the water pressure distribution information on the outer surface of the hull under different sea conditions, and a multidimensional function approximation algorithm is used to fit the water pressure distribution information to obtain a unified mathematical expression of the water pressure load on the entire ship. The unified mathematical expression is used as a unit load to input into the finite element model to obtain a full-field strain result; According to the full-field strain results, the sensor layout is optimized using an intelligent optimization algorithm to obtain layout information of the optimal measuring points, wherein the layout information includes the optimal measuring point position and the optimal measuring point direction; An influence coefficient matrix is ​​constructed using the optimized sensor layout information.

2. The method for indirect monitoring of outboard water pressure load of a ship according to claim 1, characterized in that: Use intelligent optimization algorithms to optimize sensor layout and obtain the best measurement point layout information, including: Analyzing and processing the full-field strain results using a convolutional neural network-based sensor layout optimization model to obtain a plurality of target deployment areas and corresponding optimal measurement point directions, and selecting a first number of optimal measurement point positions in each of the target deployment areas; wherein the target deployment areas are areas on the outer surface of the target vessel that are sensitive to structural response; The sensor layout optimization model also outputs a number of predicted non-target deployment areas and corresponding optimal measurement point directions, and selects a second number of the optimal measurement point positions in each of the non-target deployment areas; wherein the non-target deployment areas are located within a preset distance around the target deployment area.

3. A system for indirectly monitoring the outboard water pressure load of a ship, comprising a plurality of sensors, a processor, and a memory; characterized in that: The processor calls the computer program code in the memory to perform the following steps: Establish a finite element model to accurately describe the structural characteristics and mechanical response of the target hull, and establish a CFD model of the target hull; Calculating an outboard water pressure load distribution based on the CFD model, establishing an influence coefficient matrix based on the outboard water pressure load distribution, and establishing a relationship between the outboard water pressure load and structural response data based on the influence coefficient matrix; receiving structural response data measured by sensors arranged at optimal measuring points on the hull, and deriving a real-time outboard water pressure load based on the structural response data and the relationship; The influence coefficient matrix is ​​as follows: Where, is the influence coefficient matrix, n is the number of measuring points, m is the number of unit loads, and the elements It represents the structural response coefficient of the nth best measuring point under the unit load m; The relationship between the outboard water pressure load and the structural response data is as follows: Where, is the structural response vector measured by the sensor at each optimal measurement point, is the real-time outboard water pressure load to be inverted; The real-time outboard water pressure load is obtained based on the structural response data and the inversion relationship, including: Where, is the influence coefficient matrix The transposed matrix of is the pseudo-inverse matrix; Also includes: The CFD model is used to calculate the water pressure distribution information on the outer surface of the hull under different sea conditions, and a multidimensional function approximation algorithm is used to fit the water pressure distribution information to obtain a unified mathematical expression of the water pressure load on the entire ship. The unified mathematical expression is used as a unit load to input into the finite element model to obtain a full-field strain result; According to the full-field strain results, the sensor layout is optimized using an intelligent optimization algorithm to obtain layout information of the optimal measuring points, wherein the layout information includes the optimal measuring point position and the optimal measuring point direction; An influence coefficient matrix is ​​constructed using the optimized sensor layout information.

4. The indirect monitoring system for outboard water pressure load of a ship according to claim 3, characterized in that: Use intelligent optimization algorithms to optimize sensor layout and obtain the best measurement point layout information, including: Analyzing and processing the full-field strain results using a convolutional neural network-based sensor layout optimization model to obtain a plurality of target deployment areas and corresponding optimal measurement point directions, and selecting a first number of optimal measurement point positions in each of the target deployment areas; wherein the target deployment areas are areas on the outer surface of the target vessel that are sensitive to structural response; The sensor layout optimization model also outputs a number of predicted non-target deployment areas and corresponding optimal measurement point directions, and selects a second number of the optimal measurement point positions in each of the non-target deployment areas; wherein the non-target deployment areas are located within a preset distance around the target deployment area.

5. An electronic device, characterized in that: The electronic device comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program code implements the method according to any one of claims 1 to 4 when executed.

6. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program code is executed, the method according to any one of claims 1 to 4 is implemented.

7. A computer program product, characterized in that: The computer program product comprises a computer program code, which implements the method according to any one of claims 1 to 4 when the computer program code is executed.

Images