CN-121980856-A - Method and related device for predicting critical buckling load of deep sea pressure-resistant shell

CN121980856ACN 121980856 ACN121980856 ACN 121980856ACN-121980856-A

Abstract

The invention belongs to the field of deep sea engineering, and discloses a method and a related device for predicting critical buckling load of a deep sea pressure-resistant shell, wherein the method comprises the steps of obtaining characteristic data of a target shell; the method comprises the steps of obtaining the geometric parameters, defect characteristic information, material characteristic data and service temperature condition data of a target shell, preprocessing the characteristic data of the target shell to obtain preprocessed target shell characteristic data, taking the preprocessed target shell characteristic data as input of a preprocessed shell critical buckling load prediction model, and outputting the input of the preprocessed shell critical buckling load prediction model to obtain a critical buckling load prediction result of the target shell.

Inventors

LI XINHONG
HAN ZIYUE
ZHANG NAN
ZHANG RENREN
YU KAI
LI SIHAN

Assignees

西安建筑科技大学

Dates

Publication Date: 20260505
Application Date: 20260114

Claims (10)

1. The method for predicting critical buckling load of the deep sea pressure-resistant shell is characterized by comprising the following steps of: the method comprises the steps of obtaining characteristic data of a target shell, wherein the characteristic data of the target shell comprise geometric parameters, defect characteristic information, material characteristic data and service temperature condition data of the target shell; Preprocessing the characteristic data of the target shell to obtain preprocessed characteristic data of the target shell; taking the preprocessed target shell characteristic data as input of a pre-built shell critical buckling load prediction model, and outputting to obtain a critical buckling load prediction result of the target shell; the construction process of the pre-constructed shell critical buckling load prediction model comprises the following steps: The method comprises the steps of obtaining sample data of a sample shell, wherein the sample data of the sample shell comprise characteristic data of the sample shell and critical buckling load calculation results of the sample shell under different working conditions; Training a plurality of predetermined basic regression models by using sample data of a sample shell to obtain a plurality of trained basic regression models; And weighting and combining the plurality of trained basic regression models based on ridge regression to obtain an integrated model, and taking the integrated model as a pre-constructed shell critical buckling load prediction model.
2. The method for predicting critical buckling load of a deep sea pressure-resistant shell according to claim 1, wherein the geometric parameters of the target shell comprise the radius and the thickness of the target shell, the defect characteristic information of the target shell comprises the defect type and the defect size of the target shell, and the service temperature condition data of the target shell comprise the inner wall temperature condition and the outer wall temperature condition of the target shell.
3. The method for predicting critical buckling load of the deep sea pressure-resistant shell according to claim 1 is characterized in that the sample shell is the deep sea pressure-resistant shell with the same type or same geometric parameters as the target shell, wherein the characteristic data of the sample shell comprise the geometric parameters, defect characteristic information, material characteristic data and service temperature condition data of the sample shell; The geometrical parameters of the sample shell comprise the radius and the thickness of the sample shell, the defect characteristic information of the sample shell comprises the defect type and the defect size of the sample shell, and the service temperature condition data of the sample shell comprise the inner wall temperature condition and the outer wall temperature condition of the sample shell.
4. The method for predicting critical buckling load of the deep sea pressure-resistant shell according to claim 1, wherein the calculation result of the critical buckling load of the sample shell under different working conditions is obtained through a physical experiment method or a finite element simulation method.
5. The method for predicting critical buckling load of a deep sea pressure hull according to claim 1, wherein the plurality of predetermined basic regression models comprises a tabular prior data fitting network model, a random forest model and a support vector regression model.
6. The method for predicting critical buckling load of a deep sea pressure-resistant shell according to claim 1, wherein a five-fold cross validation method is introduced for model validation in the process of training a plurality of predetermined basic regression models and obtaining a plurality of trained basic regression models by using sample data of the sample shell.
7. A deep sea pressure housing critical buckling load prediction system, comprising: the target shell characteristic data acquisition module is used for acquiring characteristic data of the target shell, wherein the characteristic data of the target shell comprise geometric parameters, defect characteristic information, material characteristic data and service temperature condition data of the target shell; the target shell characteristic data preprocessing module is used for preprocessing the characteristic data of the target shell to obtain preprocessed target shell characteristic data; the critical buckling load prediction module is used for taking the preprocessed target shell characteristic data as input of a pre-built shell critical buckling load prediction model and outputting a critical buckling load prediction result of the target shell; the construction process of the pre-constructed shell critical buckling load prediction model comprises the following steps: The method comprises the steps of obtaining sample data of a sample shell, wherein the sample data of the sample shell comprise characteristic data of the sample shell and critical buckling load calculation results of the sample shell under different working conditions; Training a plurality of predetermined basic regression models by using sample data of a sample shell to obtain a plurality of trained basic regression models; And weighting and combining the plurality of trained basic regression models based on ridge regression to obtain an integrated model, and taking the integrated model as a pre-constructed shell critical buckling load prediction model.
8. An electronic device, comprising: a processor adapted to execute a computer program; A computer readable storage medium having a computer program stored therein, which when executed by the processor, performs the deep sea pressure hull critical buckling load prediction method according to any of claims 1-6.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the deep sea pressure housing critical buckling load prediction method according to any of claims 1-6.
10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the deep sea pressure housing critical buckling load prediction method according to any of claims 1-6.

Description

Method and related device for predicting critical buckling load of deep sea pressure-resistant shell Technical Field The invention belongs to the technical field of deep sea engineering, relates to the field of prediction of performances of deep sea pressure-resistant shells, and particularly relates to a prediction method and a related device for critical buckling load of a deep sea pressure-resistant shell. Background With the continuous development of deep sea engineering, the deep sea pressure-resistant shell plays an important role in the fields of deep sea exploration, resource exploitation, scientific research and the like, and due to extremely complex deep sea environment, the deep sea pressure-resistant shell is easily influenced by extreme temperature, pressure and the like in the service process, the deep sea pressure-resistant shell is easily defective, the ultimate bearing capacity of the deep sea pressure-resistant shell is reduced, and even the shell is invalid in severe cases, wherein the critical buckling load is a key index for evaluating the ultimate bearing capacity of the deep sea pressure-resistant shell, and when the external load of the deep sea pressure-resistant shell reaches the critical buckling load, the destabilization damage occurs, so that the accurate evaluation of the critical buckling load is very important for guaranteeing the structural safety of the deep sea pressure-resistant shell. At present, a physical test method and a finite element simulation method are mainly adopted for evaluating critical buckling load of the deep sea pressure-resistant shell, wherein the physical test method is used for judging the critical buckling load by establishing shell entity models in different states and applying different pressures according to actual conditions, and the finite element simulation method is used for simulating stress conditions under different working conditions by establishing the finite element models of the deep sea pressure-resistant shell so as to evaluate the critical buckling load. However, the existing assessment method generally needs to consume a large amount of time and cost, and is extremely easy to influence the accuracy of the assessment result, wherein the physical test method is limited by factors such as test cost, data availability and the like, the overall cost of the test cannot be fully and accurately reflected in the actual deep sea environment, particularly, the test under the deep sea environment needs expensive equipment and high-end technical support, the test often needs to simulate extreme conditions such as real high pressure, low temperature and corrosion in the deep sea due to extremely complex environment, the cost of each test is extremely high, in addition, a plurality of entity models are generally required to be established for the test to simulate different working conditions and environment conditions, the cost is increased, the test period is prolonged, researchers generally need to perform a large amount of repeated tests to ensure the representativeness and accuracy of data, the overall cost of the test is further improved, the test can only simulate limited working conditions in the test, and the environment change in actual application cannot be fully reproduced due to the variability of the deep sea environment, and the limitation can not fully reflect the actual load of the actual deep sea environment in the actual deep sea environment. In addition, the finite element simulation method faces the trade-off problem between modeling complexity and calculation resource consumption, analysis is difficult to complete in reasonable time while model accuracy is guaranteed, specifically, the deep sea pressure-resistant shell is complex in structure and influenced by various working conditions, different material properties, geometric characteristics and changeable defect working conditions are needed to be considered in finite element modeling, so that the modeling process is extremely complex, for example, the finite element model needs to be subjected to a large number of assumptions and simplification to complete analysis in acceptable calculation time in consideration of factors such as temperature, corrosion and cracks, deviation of the model from actual conditions can be caused due to simplification, accuracy of analysis results is influenced, fine division of grids is needed to improve model accuracy, calculation capacity is greatly increased, consumption of calculation resources can exceed practical available calculation capacity for large-scale or higher-accuracy simulation, analysis processes are time-consuming and cannot be completed in reasonable time, and the problem of calculation resource consumption is faced by the finite element analysis method in critical buckling assessment under the processing of complex sea environment. In view of the foregoing, there is a need for a method for effectively and accurately evalua