Method for measuring internal stress of observation window of bathyscaphe and related device

Through the finite element simulation method assisted by neural network, the efficient and accurate problems of internal stress measurement in the deep-sea submersible observation window are solved, and efficient and convenient stress distribution calculation is achieved, which is suitable for light-transmitting structures and avoids the influence of environmental factors.

CN119085907APending Publication Date: 2024-12-06CHINA SPECIAL EQUIP INSPECTION & RES INST
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411186364.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art has problems such as high efficiency, convenience and insufficient resistance to environmental factors in the internal stress measurement of deep-sea submersible observation windows. In particular, the strain gauge method has limited surface stress measurement, the photoelastic method has complex structure and low accuracy. Infrared measurement methods are not suitable for light-transmitting structures and are costly.

Method used

Using the finite element simulation method assisted by neural network, the surface stresses of several measurement points are obtained, the stress influence parameters are determined, and the finite element simulation model of the deep-sea submersible observation window is generated, and the finite element simulation calculation is performed to obtain the stress distribution of the observation window. Includes internal and surface stress.

Benefits of technology

It realizes the efficient and convenient measurement of internal stress in the deep-sea submersible observation window, high accuracy, and can resist the influence of environmental factors, avoiding damage to the observation window and complex device deployment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085907A_ABST
    Figure CN119085907A_ABST
Patent Text Reader

Abstract

The invention discloses a method for measuring internal stress of an observation window of a bathyscaph and a related device, and relates to the technical field of bathyscaph application, surface stress of a plurality of measuring points on the observation window of the bathyscaph is used as input, and a trained prediction model is used for determining stress influence parameters; and generating a finite element simulation model of the deep sea submersible observation window based on the stress influence parameters, and performing finite element simulation calculation by using the finite element simulation model to obtain stress distribution of the deep sea submersible observation window. The stress distribution comprises the internal stress of each internal position point and the surface stress of each surface position point of the observation window of the bathyscaphe, only the surface stress of a plurality of measuring points needs to be measured, strain gauges do not need to be arranged on the whole plane of the observation window, complex measuring devices do not need to be deployed either, and the method is efficient, convenient and fast and can be widely applied to the field of underwater observation. And the influence of environmental factors can be resisted, and the precision is high.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of deep-sea submersible application technology, and in particular to a method for measuring internal stress of a deep-sea submersible observation window assisted by a neural network and a related device. Background Art

[0002] Submersibles are the main tools for underwater operations, integrating functions such as detection, mining, storage and transportation. The detection and mining of rich natural resources in the vast ocean has put forward an urgent need for the research and development of high-performance deep-sea submersibles. Due to the harsh working conditions in the deep sea, long working hours and the continuous high environmental water pressure in the working environment, the structural research of deep-sea submersibles needs to consider not only the functionality of each part of the structure, but also its safety in the working environment, including sealing and structural mechanical properties. Among them, an important structure in the deep-sea submersible is the observation window, which can provide researchers with a window to observe the deep-sea environment, which is convenient for deep-sea submersibles to carry out underwater operations. The commonly used observation window material is PMMA (Polymethyl methacrylate, organic glass). In order to fully grasp the working state of the observation window, it is generally necessary to measure the overall stress distribution of the observation window, not only the surface stress but also the internal stress. At the same time, the measurement results also provide data support for the research on the reliability and structural design of the observation window.

[0003] At present, the surface stress state of the observation window structure can be directly measured by relatively simple experimental means. For example, the surface stress at the measuring point can be obtained by combining the strain gauge measurement data with relevant theories. The internal stress state of the observation window structure can also be measured by experimental means, but the experimental means are relatively complicated. For light-transmitting structures, the photoelastic method is generally used, and for opaque structures, the near-infrared measurement method is generally used.

[0004] However, in actual measurement, the above methods have certain limitations. The strain gauge method can only calculate the surface stress at the measuring point, and cannot measure the stress of the entire plane and the internal structure. If you want to obtain the stress of the entire plane, you need to set strain gauges at every position point of the entire plane, which is very complicated. Since the strain gauges are mostly pasted to the measuring points by strong glue, it will cause great damage to the observation window, and it can only measure the surface stress, and cannot measure the stress of the internal structure. The measurement device of the photoelastic method has a complex structure and is difficult to deploy. Its measurement results are greatly affected by environmental factors such as noise and have low accuracy. The near-infrared measurement method is suitable for the measurement of opaque structures, and the role of the observation window is to provide researchers with a window to observe the deep-sea environment. Researchers observe the deep-sea environment through the observation window. The material of the observation window is generally PMMA organic glass, so the observation window is a light-transmitting structure. The near-infrared measurement method is not suitable for measuring the observation window, and the sensitivity is low but the cost is high. At the same time, the repeatability of all methods is poor.

[0005] In summary, the measurement of internal stress of deep-sea submersible observation windows has deficiencies in terms of efficiency, convenience, and resistance to the influence of environmental factors. An improved measurement technology is urgently needed to circumvent the above problems. Summary of the invention

[0006] The purpose of the present application is to provide a method and a related device for measuring the internal stress of a deep-sea submersible observation window, which can efficiently and conveniently measure the internal stress of a deep-sea submersible observation window with high measurement accuracy.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for measuring internal stress of a deep-sea submersible observation window, the method comprising:

[0009] Obtaining surface stress at a plurality of measuring points; the measuring points are located on the observation window of the deep-sea submersible;

[0010] Taking the surface stress of all the measuring points as input, the trained prediction model is used to determine the stress influencing parameters; the stress influencing parameters are the parameters that affect the stress calculation in the finite element simulation model of the deep-sea submersible observation window;

[0011] A finite element simulation model of a deep-sea submersible observation window is generated based on the stress influencing parameters, and a finite element simulation calculation is performed using the finite element simulation model to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0012] Optionally, the stress influencing parameters are relevant parameters of the material constitutive model or relevant parameters of the boundary conditions in the finite element simulation model of the deep-sea submersible observation window; the relevant parameters of the material constitutive model are the elastic modulus or the viscosity coefficient in the viscoelastic model; the relevant parameters of the boundary conditions are the spring stiffness coefficient of the spring boundary conditions or the friction coefficient and contact stiffness of the contact boundary conditions.

[0013] Optionally, before using the surface stress of all the measuring points as input and using the trained prediction model to determine the stress influencing parameter, the method for measuring the internal stress of the deep-sea submersible observation window further includes:

[0014] Acquire simulated surface stresses of several sample measuring points under different values ​​of stress influencing parameters; the sample measuring points are at the same position as the measuring points; the simulated surface stresses are obtained through finite element simulation analysis, and the finite element simulation analysis is performed by using a finite element simulation model to obtain simulated surface stresses of several sample measuring points on the finite element simulation model under the stress influencing parameters of the values ​​after each adjustment of the stress influencing parameters;

[0015] Taking the simulated surface stress as input and the stress influencing parameter as a label, the initial prediction model is trained using the simulated surface stress of several sample measuring points under different values ​​of the stress influencing parameter to obtain a trained prediction model.

[0016] Optionally, the trained prediction model adopts a neural network, and the neural network includes an input layer, a hidden layer and an output layer connected in sequence.

[0017] Optionally, the measuring point is an arbitrary position point on the surface of the observation window of the deep-sea submersible.

[0018] Optionally, after obtaining the stress distribution of the deep-sea submersible observation window, the deep-sea submersible observation window stress measurement method further includes:

[0019] Obtaining surface stresses at a plurality of verification points; the verification points are located on the observation window of the deep-sea submersible;

[0020] For each of the verification points, selecting the surface stress of a position point corresponding to the position of the verification point in the stress distribution as the surface stress to be compared at the verification point;

[0021] The surface stresses at several verification points are compared with the surface stress to be compared to verify the accuracy of the stress distribution.

[0022] In a second aspect, the present application provides a device for measuring internal stress of a deep-sea submersible observation window, the device comprising:

[0023] A data acquisition module, used to acquire surface stress at a plurality of measuring points; the measuring points are located on the observation window of the deep-sea submersible;

[0024] A prediction module, used to use the surface stress of all the measuring points as input and determine stress influencing parameters using a trained prediction model; the stress influencing parameters are parameters that affect stress calculation in a finite element simulation model of a deep-sea submersible observation window;

[0025] A simulation calculation module is used to generate a finite element simulation model of a deep-sea submersible observation window based on the stress influencing parameters, and use the finite element simulation model to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0026] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for measuring internal stress in an observation window of a deep-sea submersible.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for measuring internal stress in an observation window of a deep-sea submersible.

[0028] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for measuring internal stress in an observation window of a deep-sea submersible.

[0029] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0030] The present application provides a method and related device for measuring the internal stress of a deep-sea submersible observation window. The method takes the surface stress of several measuring points on the deep-sea submersible observation window as input, uses a trained prediction model to determine stress influencing parameters, generates a finite element simulation model of the deep-sea submersible observation window based on the stress influencing parameters, and uses the finite element simulation model to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window. The stress distribution includes the internal stress of each internal position point and the surface stress of each surface position point of the deep-sea submersible observation window. It is only necessary to measure the surface stress of several measuring points, and there is no need to set strain gauges on the entire plane of the observation window, nor is there any need to deploy complex measuring devices. The method is efficient, convenient, and can resist the influence of environmental factors with high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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 of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is an application environment diagram of a method for measuring internal stress in a deep-sea submersible observation window provided in Example 1 of the present application.

[0033] Figure 2 A schematic flow chart of a method for measuring internal stress in a deep-sea submersible observation window provided in Example 1 of the present application.

[0034] Figure 3 A detailed flow chart of a method for measuring internal stress of a deep-sea submersible observation window provided in Example 1 of the present application.

[0035] Figure 4 A schematic diagram of the detailed dimensions of the observation window provided in Example 1 of the present application.

[0036] Figure 5 This is a schematic diagram of the stress distribution results obtained by finite element simulation calculation of the observation window provided in Example 1 of the present application.

[0037] Figure 6 A schematic diagram of the functional modules of a device for measuring internal stress in an observation window of a deep-sea submersible provided in Example 2 of the present application.

[0038] Figure 7 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] Example 1

[0041] The method for measuring internal stress of a deep-sea submersible observation window provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers. The terminal can send the surface stress of several measuring points to be processed to the server. After the server receives the surface stress of several measuring points to be processed, for the surface stress of several measuring points to be processed, the server uses the surface stress of all measuring points as input, and uses the trained prediction model to determine the stress influencing parameters; based on the stress influencing parameters, a finite element simulation model of the deep-sea submersible observation window is generated, and the finite element simulation model is used to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window. The server can feedback the obtained stress distribution of the deep-sea submersible observation window to the terminal.

[0042] In addition, in some embodiments, the method for measuring the internal stress of the deep-sea submersible observation window can also be implemented independently by a server or a terminal. For example, the terminal can directly process the surface stress of several measuring points to be processed, or the server can obtain the surface stress of several measuring points to be processed from the data storage system and process the surface stress of several measuring points to be processed.

[0043] like Figure 2 As shown, a method for measuring the internal stress of a deep-sea submersible observation window is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 Taking the server in the example as an example, the method for measuring the internal stress of the deep-sea submersible observation window includes the following steps:

[0044] Step S1, obtaining the surface stress of a plurality of measuring points; the measuring points are located on the observation window of a deep-sea submersible.

[0045] Step S2, taking the surface stress of all the measuring points as input, and using the trained prediction model to determine the stress influencing parameters; the stress influencing parameters are the parameters that affect the stress calculation in the finite element simulation model of the deep-sea submersible observation window.

[0046] Step S3, generating a finite element simulation model of the deep-sea submersible observation window based on the stress influencing parameters, and performing finite element simulation calculations using the finite element simulation model to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0047] By implementing the above steps S1 to S3, this embodiment can provide an efficient and convenient method for measuring the internal stress of the deep-sea submersible observation window. By combining the trained prediction model with the finite element simulation calculation, the stress distribution of the deep-sea submersible observation window is calculated. It is only necessary to measure the surface stress of several measuring points. There is no need to set strain gauges on the entire plane of the observation window, and there is no need to deploy complex measuring devices. The method is efficient, convenient, and can resist the influence of environmental factors with high accuracy.

[0048] In S1, the surface stress of several measuring points is obtained, specifically including: for each measuring point, the surface stress obtained by measuring the measuring point is obtained. The measuring point can be measured by a strain gauge, specifically, the strain gauge is set on the measuring point, the measuring point is measured by the strain gauge, the strain of the measuring point is obtained, and the surface stress of the measuring point is further calculated based on the strain.

[0049] The measuring point can be located at any position of the observation window, that is, the measuring point is any position point on the surface of the observation window of the deep-sea submersible. For example, the measuring point is the center point of the inner surface or outer surface of the observation window of the deep-sea submersible.

[0050] In S2, the stress influencing parameters are the relevant parameters of the material constitutive model or the relevant parameters of the boundary conditions in the finite element simulation model of the deep-sea submersible observation window. The relevant parameters of the material constitutive model are the elastic modulus or the viscosity coefficient in the viscoelastic model, and the relevant parameters of the boundary conditions are the spring stiffness coefficient of the spring boundary condition or the friction coefficient and contact stiffness of the contact boundary condition.

[0051] Before using the surface stress of all measuring points as input and using the trained prediction model to determine the stress influencing parameters, the method for measuring the internal stress of the deep-sea submersible observation window of this embodiment further includes:

[0052] (1) The simulated surface stress of several sample measuring points under different values ​​of the stress influencing parameter is obtained. The sample measuring point has the same position as the measuring point. The simulated surface stress is obtained through finite element simulation analysis. The finite element simulation analysis is performed by using a finite element simulation model to perform finite element simulation calculation after each adjustment of the value of the stress influencing parameter, and the simulated surface stress of several sample measuring points on the finite element simulation model under the stress influencing parameter of the value is obtained.

[0053] This embodiment establishes a corresponding finite element simulation model according to the structure of the deep-sea submersible observation window, and sets the material properties, load conditions and boundary conditions of the finite element simulation model according to the actual situation. The material properties are the same as the material of the deep-sea submersible observation window, the load conditions are the same as the load conditions of the deep-sea working environment, and the boundary conditions are applied to each boundary surface of the finite element simulation model. Before the formal calculation, the mesh size of the finite element simulation model is subjected to convergence analysis to determine the most suitable mesh size for calculation. Then, by changing the value of the stress influence parameter within a certain reasonable range, stress influence parameters with different values ​​are formed, and finite element simulation calculations are performed using finite element simulation models with stress influence parameters with different values, and the simulated surface stress at the position of the sample measuring point is correspondingly extracted to obtain the simulated surface stress of several sample measuring points under each value of the stress influence parameter.

[0054] (2) Taking the simulated surface stress as input and the stress influencing parameter as a label, the initial prediction model is trained using the simulated surface stress of several sample measurement points under different values ​​of the stress influencing parameter to obtain a trained prediction model.

[0055] In this embodiment, the trained prediction model adopts a neural network, and the neural network includes an input layer, a hidden layer and an output layer connected in sequence. The structure of the initial prediction model is exactly the same as that of the trained prediction model.

[0056] The calculation principle of the neural network is to perform mathematical operations on the input data through neurons, and through continuous training, the output results are gradually approached to the real results. In the process of training the neural network, optimization methods such as back propagation algorithm and gradient descent method are generally used to iterate and update the weights of the neural network, find the optimal numerical solution of the neural network, and thus establish a calculation relationship between input and output. This embodiment uses the values ​​of the stress influence parameters of the known finite element simulation model and the simulated surface stress of the corresponding sample measuring points to train the neural network, wherein the input layer of the neural network receives the simulated surface stress of all sample measuring points, the hidden layer performs information processing and feature extraction through multiple layers of neurons, and the output layer generates the predicted values ​​of the corresponding stress influence parameters, and performs loss calculation with the values ​​of the stress influence parameters, and updates the neural network until the iteration termination condition is reached to obtain a trained prediction model. The iteration termination condition can be reaching the maximum number of iterations.

[0057] After obtaining the trained prediction model, this embodiment can directly use the surface stress of all measuring points as input, use the trained prediction model to determine the values ​​of stress influencing parameters, and generate a finite element simulation model of the deep-sea submersible observation window based on the values ​​of stress influencing parameters, that is, the stress influencing parameters in the finite element simulation model of the deep-sea submersible observation window adopt the values ​​predicted by the trained prediction model, and use the finite element simulation model to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window, where the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0058] After obtaining the stress distribution of the deep-sea submersible observation window, the deep-sea submersible observation window stress measurement method of this embodiment also includes: obtaining the surface stress of several verification points, where the verification points are located on the deep-sea submersible observation window; for each verification point, selecting the surface stress of a position point corresponding to the position of the verification point in the stress distribution as the surface stress to be compared of the verification point; comparing the surface stress of several verification points with the surface stress to be compared to verify the accuracy of the stress distribution.

[0059] This embodiment uses the learning and computing capabilities of a neural network to calculate the stress distribution of the observation window, and can efficiently and conveniently calculate the stress distribution of the observation window of a deep-sea submersible with high calculation accuracy.

[0060] The following, such as Figure 3 As shown, this embodiment takes the spring stiffness coefficient of the spring boundary condition as an example to further introduce the internal stress measurement method of the deep-sea submersible observation window of this embodiment:

[0061] (1) Within a reasonable range, a large number of values ​​of the spring stiffness coefficient of the spring boundary condition are taken, and finite element simulation calculations are performed to extract the surface stress of the sample measuring point. The surface stress of the sample measuring point and the values ​​of the spring stiffness coefficient of the spring boundary condition are used to train the initial prediction model to obtain a trained prediction model.

[0062] This embodiment establishes a corresponding finite element simulation model according to the structure of the deep-sea submersible observation window, and sets the material properties, load conditions and boundary conditions of the finite element simulation model according to the actual situation. The material properties are the same as the material of the deep-sea submersible observation window, the load conditions are the same as the load conditions of the deep-sea working environment, and the boundary conditions adopt spring boundary conditions, which are applied to each boundary surface of the finite element simulation model. By changing the spring stiffness coefficient of the spring boundary condition within a certain reasonable range, boundary conditions of different strengths are formed. Finite element simulation calculations are performed using the finite element simulation models under boundary conditions of different strengths, and the simulated surface stress at the sample measuring point position is correspondingly extracted to obtain the simulated surface stress of several sample measuring points under each value of the spring stiffness coefficient.

[0063] With the simulated surface stress as input and the spring stiffness coefficient as a label, the initial prediction model is trained using the simulated surface stress of several sample measurement points under each value of the spring stiffness coefficient to obtain a trained prediction model.

[0064] This embodiment uses the values ​​of the spring stiffness coefficient of the spring boundary conditions of the known finite element simulation model and the simulated surface stress of the corresponding sample measuring points to train the neural network, wherein the input layer of the neural network receives the simulated surface stress of all sample measuring points, the hidden layer performs information processing and feature extraction through multiple layers of neurons, and the output layer generates the predicted value of the spring stiffness coefficient of the corresponding spring boundary condition, performs loss calculation with the value of the spring stiffness coefficient under the spring boundary condition, and updates the neural network until the iteration termination condition is reached to obtain a trained prediction model.

[0065] (2) The surface stress of several measuring points is obtained through experiments. The measuring points are located on the observation window of the deep-sea submersible, and the measuring points should include the finite element measuring points used to train the neural network model, that is, the simulation measuring points. The surface stress of the measuring points is used as input, and the spring stiffness coefficient of the spring boundary condition is determined using the trained prediction model.

[0066] (3) Based on the spring stiffness coefficient, spring boundary conditions are applied to the finite element simulation model of the deep-sea submersible observation window, and the finite element simulation model is used to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window. The stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0067] During finite element simulation calculation, multiple parameters have an impact on the stress calculation results. Considering that the treatment method of the contact interface between the observation window and the window seat has a great impact on the structural stress calculation results of the observation window, this embodiment takes the study of the spring stiffness coefficient of the spring boundary condition as an example for detailed discussion. In practical application, it includes but is not limited to the spring stiffness coefficient parameter, and related parameters of the material constitutive model can also be used, such as the elastic modulus, the viscosity coefficient in the viscoelastic model, etc.; related parameters of other boundary conditions can also be used, such as the friction coefficient and contact stiffness of the contact boundary condition, etc.

[0068] This embodiment can also use a test piece to verify the performance of the method for measuring the internal stress of the deep-sea submersible observation window of this embodiment, including the following steps:

[0069] (1) Experimental test: First, use the load control module to apply pressure to the test piece, use the strain gauge to measure and record the surface stress at multiple test points on the test piece, and wait for the next step. Special attention should be paid to the test points, which should include the positions of the sample test points of the finite element simulation model.

[0070] During the test, the surface stress at multiple test points was obtained through stress measurement test. The stress measurement test is to apply the load of deep-sea working environment to the test piece of the deep-sea submersible observation window, and obtain the actual surface stress obtained by measuring the test points on the test piece. The material and size of the test piece are the same as those of the deep-sea submersible observation window.

[0071] In this embodiment, the test piece is processed according to the material and size of the deep-sea submersible observation window. The test piece has the same material and size as the deep-sea submersible observation window. Under the load conditions simulating the deep-sea working environment, the stress measurement test of the test piece is designed. The basic device used for the stress measurement test includes a load control module, a strain gauge and its data acquisition device and a test piece. The process of the stress measurement test includes: first, installing a strain gauge at the test measuring point position on the test piece, and connecting the strain gauge to the data acquisition device. Then, the load control module is used to apply a load to the outer surface area of ​​the test piece (i.e., the outer surface of the observation window), simulating the water pressure of the observation window in the deep-sea working environment, and real-time monitoring and maintaining a stable load input. Finally, the strain data of the test measuring point is obtained through the strain gauge, and the data acquisition device extracts the strain data, and further calculates the actual surface stress of the test measuring point.

[0072] There should be no less than two test points. As an example, the test points are the center point of the inner surface and the center point of the outer surface of the deep-sea submersible observation window, that is, Figure 4 The center point of the plane represented by the straight line with a side length of 100 and a side length of 320. The surface stress data of the center point of the outer surface is used to provide the trained prediction model to calculate the spring stiffness coefficient; the surface stress data of the center point of the inner surface is used to compare with the stress distribution obtained by finite element simulation calculation to verify the correctness of the internal stress measurement method of the deep-sea submersible observation window proposed in this embodiment. Of course, other position points on the observation window can also be selected as test measurement points as needed.

[0073] (2) Parameter prediction: The surface stress of the test point obtained in the test at the same position as the sample measurement point of the finite element simulation model is input into the trained prediction model, and the spring stiffness coefficient of the spring boundary condition of the predicted finite element simulation model can be obtained. The spring stiffness coefficient is used to apply boundary conditions to the finite element simulation model, and the material properties and load conditions of the finite element simulation model are set at the same time. The finite element simulation model is further used to perform finite element simulation calculations to obtain the stress distribution of the test piece.

[0074] (3) Error analysis: During the test, multiple test points were selected, strain gauges were attached to each test point, and the stress state of the test point was measured. The surface stress of some test points was applied to the parameter prediction step. The finite element simulation model was established based on the predicted spring stiffness coefficient parameter and finite element simulation calculation was performed to obtain the stress distribution. This embodiment further extracted the surface stress of the remaining test points and compared it with the surface stress of the corresponding position in the stress distribution obtained by simulation calculation (i.e., corresponding to the position of the remaining test points), and performed error calculation, so as to verify the accuracy of the calculated spring stiffness coefficient parameter.

[0075] This embodiment combines experimental testing with finite element simulation calculations and utilizes the learning and computing capabilities of a neural network to calculate the stress distribution of the observation window. It is possible to efficiently and conveniently calculate the stress distribution of the observation window of a deep-sea submersible with high calculation accuracy.

[0076] Compared with the prior art, this embodiment has the following advantages: the measurement of the internal stress state of the observation window no longer relies solely on experiments, but adopts a combination of finite element simulation and neural network technology, and proposes a new measurement method. The setting of the test measurement device is relatively simple, and only a load application device, a strain gauge and a data acquisition device are required, and the demand for test result data is small, and there is no need to set a large number of measurement points and a large number of repeated tests. At the same time, the distribution of internal stress of the observation window can be directly calculated using the finite element simulation model, and the display of the stress distribution results can be more intuitive and clear. In short, the measurement of the internal stress of the observation window of a deep-sea submersible by this embodiment is simpler and more convenient, with low cost and clear results. At the same time, the method has a wide range of applications and is applicable to different influencing parameters.

[0077] Assume that the shape of a certain observation window is a truncated cone, and the specific dimensions are as follows: Figure 4 As shown. The outer surface of the observation window is subjected to uniform pressure. The material parameters of the observation window are known. The working state of the side is fixed during the test. The spring boundary condition is used in the simulation calculation, but the spring stiffness coefficient of the spring boundary condition is unknown. The spring stiffness coefficient is selected within a suitable range. The more values ​​are selected, the greater the amount of calculation but the more accurate the calculation result. Finite element simulation calculations are performed on the above values ​​respectively, and the surface stress at the center point of the outer surface of the observation window under the corresponding values ​​is extracted to train the neural network and obtain a trained prediction model.

[0078] The observation window is tested by pasting two strain gauges on the observation window, the positions of which are the center point of the outer surface of the observation window and the center point of the inner surface of the observation window, respectively, and measuring the surface stress at the two points.

[0079] The surface stress measured at the center point of the outer surface of the observation window is input into the trained prediction model, and the predicted spring stiffness coefficient is output. The predicted spring stiffness coefficient is used to perform finite element simulation calculation of the observation window. The stress distribution result of the observation window is as follows: Figure 5 As shown in Table 1, the simulation result of the center point of the inner surface of the observation window (i.e., the surface stress at the center point of the inner surface in the stress distribution) is extracted and compared with the measured result (i.e., the surface stress at the center point of the inner surface obtained by the experimental test), as shown in Table 1.

[0080] Table 1 Comparison of simulation results and measured results

[0081] Simulation results (MPa) Measured results (MPa) error 11.8066293 11.8066321 0%

[0082] It can be seen that the simulation results under the predicted spring stiffness coefficient are consistent with the measured results, and the relative error control is very small. Figure 5 The stress distribution of the observation window shown can more accurately represent the actual stress distribution state of the observation window.

[0083] The embodiment of the present application also provides an application scenario, which applies the above-mentioned method for measuring internal stress of the deep-sea submersible observation window. Specifically, the method for measuring internal stress of the deep-sea submersible observation window provided by this embodiment can be applied in the internal stress measurement scenario, and the internal stress measurement scenario includes a data acquisition link and a data processing link. The data acquisition link is used to obtain the surface stress of several measuring points, and the data processing link is used to determine the stress distribution of the deep-sea submersible observation window using a trained prediction model and finite element simulation calculation. The method for measuring internal stress of the deep-sea submersible observation window provided by this embodiment belongs to the data processing link.

[0084] Example 2

[0085] Based on the same inventive concept, the embodiment of the present application also provides a deep-sea submersible observation window internal stress measurement device for implementing the deep-sea submersible observation window internal stress measurement method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the deep-sea submersible observation window internal stress measurement device embodiment provided below can refer to the above limitations on the deep-sea submersible observation window internal stress measurement method, and will not be repeated here.

[0086] like Figure 6 As shown, a device for measuring internal stress of a deep-sea submersible observation window is provided, comprising:

[0087] The data acquisition module M1 is used to acquire the surface stress of a plurality of measuring points; the measuring points are located on the observation window of the deep-sea submersible.

[0088] The prediction module M2 is used to use the surface stress of all the measuring points as input and determine the stress influencing parameters using the trained prediction model; the stress influencing parameters are the parameters that affect the stress calculation in the finite element simulation model of the deep-sea submersible observation window.

[0089] The simulation calculation module M3 is used to generate a finite element simulation model of the deep-sea submersible observation window based on the stress influencing parameters, and use the finite element simulation model to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

[0090] Example 3

[0091] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data to be processed. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the internal stress measurement method of the deep-sea submersible observation window described in Example 1.

[0092] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0093] In an exemplary embodiment, a computer device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for measuring internal stress of a deep-sea submersible observation window as described in Example 1.

[0094] Example 4

[0095] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for measuring internal stress of an observation window of a deep-sea submersible described in Embodiment 1 is implemented.

[0096] Example 5

[0097] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for measuring internal stress of an observation window of a deep-sea submersible as described in Embodiment 1.

[0098] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for measuring internal stress of a deep-sea submersible observation window. It is characterized in that The method for measuring internal stress of a deep-sea submersible observation window comprises: Obtaining surface stress at a plurality of measuring points; the measuring points are located on the observation window of the deep-sea submersible; Taking the surface stress of all the measuring points as input, the trained prediction model is used to determine the stress influencing parameters; the stress influencing parameters are the parameters that affect the stress calculation in the finite element simulation model of the deep-sea submersible observation window; A finite element simulation model of a deep-sea submersible observation window is generated based on the stress influencing parameters, and a finite element simulation calculation is performed using the finite element simulation model to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

2. The method for measuring internal stress of a deep-sea submersible observation window according to claim 1, It is characterized in that The stress influencing parameters are relevant parameters of the material constitutive model or relevant parameters of the boundary conditions in the finite element simulation model of the deep-sea submersible observation window; the relevant parameters of the material constitutive model are the elastic modulus or the viscosity coefficient in the viscoelastic model; the relevant parameters of the boundary conditions are the spring stiffness coefficient of the spring boundary conditions or the friction coefficient and contact stiffness of the contact boundary conditions.

3. The method for measuring internal stress of a deep-sea submersible observation window according to claim 1, It is characterized in that Before determining the stress influencing parameters using the trained prediction model using the surface stress of all the measuring points as input, the method for measuring the internal stress of the deep-sea submersible observation window further includes: Acquire simulated surface stresses of several sample measuring points under different values ​​of stress influencing parameters; the sample measuring points are at the same position as the measuring points; the simulated surface stresses are obtained through finite element simulation analysis, and the finite element simulation analysis is performed by using a finite element simulation model to obtain simulated surface stresses of several sample measuring points on the finite element simulation model under the stress influencing parameters of the values ​​after each adjustment of the stress influencing parameters; Taking the simulated surface stress as input and the stress influencing parameter as a label, the initial prediction model is trained using the simulated surface stress of several sample measuring points under different values ​​of the stress influencing parameter to obtain a trained prediction model.

4. The method for measuring internal stress of a deep-sea submersible observation window according to claim 1, It is characterized in that The trained prediction model adopts a neural network, and the neural network includes an input layer, a hidden layer and an output layer connected in sequence.

5. The method for measuring internal stress of a deep-sea submersible observation window according to claim 1, It is characterized in that The measuring point is an arbitrary position point on the surface of the observation window of the deep-sea submersible.

6. The method for measuring internal stress of a deep-sea submersible observation window according to claim 1, It is characterized in that After obtaining the stress distribution of the deep-sea submersible observation window, the deep-sea submersible observation window stress measurement method further includes: Obtaining surface stresses at a plurality of verification points; the verification points are located on the observation window of the deep-sea submersible; For each of the verification points, selecting the surface stress of a position point corresponding to the position of the verification point in the stress distribution as the surface stress to be compared at the verification point; The surface stresses at several verification points are compared with the surface stress to be compared to verify the accuracy of the stress distribution.

7. A device for measuring internal stress of a deep-sea submersible observation window, It is characterized in that The deep-sea submersible observation window internal stress measuring device comprises: A data acquisition module, used to acquire surface stress at a plurality of measuring points; the measuring points are located on the observation window of the deep-sea submersible; A prediction module, used to use the surface stress of all the measuring points as input and determine stress influencing parameters using a trained prediction model; the stress influencing parameters are parameters that affect stress calculation in a finite element simulation model of a deep-sea submersible observation window; A simulation calculation module is used to generate a finite element simulation model of a deep-sea submersible observation window based on the stress influencing parameters, and use the finite element simulation model to perform finite element simulation calculations to obtain the stress distribution of the deep-sea submersible observation window; the stress distribution includes the internal stress of each internal position point of the deep-sea submersible observation window and the surface stress of each surface position point.

8. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for measuring internal stress of a deep-sea submersible observation window according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for measuring internal stress of a deep-sea submersible observation window according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method for measuring internal stress of a deep-sea submersible observation window according to any one of claims 1 to 6 is implemented.

Citation Information

Cited By

  • Manned submersible observation window stress prediction method based on machine learning

    CN119378337A

  • Design method for observation window of full-sea-depth manned submersible

    CN119577976A

  • Design Method of Observation Window for Full Ocean Depth Manned Submersible

    CN119577976B