Storage tank container pressure deformation early warning method and device, computer equipment and medium

Abstract

The invention relates to a storage tank container pressure deformation early warning method and device, computer equipment and a medium, and the method comprises the steps: obtaining a three-dimensional model of a storage tank container; performing hydrodynamic analysis on the fluid in the storage tank container based on the three-dimensional model to obtain a hydrodynamic analysis result; carrying out stress analysis on the storage tank container according to the three-dimensional model and the hydrodynamic analysis result to obtain a stress analysis result; acquiring collected pressure deformation real-time data of the storage tank container, and obtaining pressure deformation prediction data of the storage tank container in the next prediction period based on the pressure deformation real-time data, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result; and if it is judged that the pressure deformation real-time data and the pressure deformation prediction data are abnormal, a preset alarm message is pushed. According to the whole scheme, efficient and accurate pressure deformation early warning of the storage tank container can be realized.

Description

Technical Field

[0001] The present application relates to the field of intelligent early warning technology, and in particular to a method, device, computer equipment, storage medium and computer program product for early warning of pressure deformation of a storage tank container. Background Art

[0002] As an indispensable equipment in the chemical, petroleum, food and other industries, storage tanks are mainly used to store liquids or gases safely and efficiently. However, in actual applications, storage tanks face a variety of potential safety risks. Due to changes in internal pressure and temperature and the complex influence of the external environment, the tank structure may be deformed, cracked or even leaked, and in extreme cases, it may cause catastrophic accidents such as explosions. These accidents will not only cause serious casualties and property losses, but also cause long-term pollution and damage to the surrounding environment.

[0003] In order to ensure the safe operation of storage tanks, traditional monitoring methods mainly rely on manual inspections and equipment detection. However, this method has obvious limitations. On the one hand, manual inspections are inefficient and it is difficult to achieve real-time monitoring of the status of storage tanks; on the other hand, although equipment detection can provide certain data support, it is costly and there is a risk of missed detection and false detection. Especially in extreme environments, such as high temperature and high pressure, the stability and accuracy of traditional monitoring equipment are often difficult to guarantee.

[0004] In recent years, with the continuous development of sensor technology and monitoring systems, more and more storage tanks have begun to adopt automated monitoring methods. However, these systems still face many challenges in practical applications. First of all, the accuracy and long-term stability of the sensor are the key to achieving efficient monitoring, but traditional sensor technology often has difficulty maintaining stable performance in complex and changeable storage tank environments. False alarms or missed alarms occur from time to time, which poses a great hidden danger to the safe operation of storage tanks. Therefore, there is an urgent need for an efficient and accurate early warning solution for pressure deformation of storage tank containers. Summary of the invention

[0005] Based on this, it is necessary to provide an efficient and accurate tank container pressure deformation warning method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a method for early warning of pressure deformation of a storage tank container. The method comprises:

[0007] Obtain a 3D model of the tank container;

[0008] Performing fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain fluid dynamics analysis results;

[0009] Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result;

[0010] Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result;

[0011] If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

[0012] In one embodiment, obtaining the three-dimensional model of the storage tank container includes:

[0013] Obtain 3D scanning data of storage tank containers;

[0014] Extracting geometric shape features, material property features, and internal structure features of the storage tank container based on the three-dimensional scanning data;

[0015] A three-dimensional model of the storage tank container is constructed according to the geometric shape characteristics, the material property characteristics and the internal structure characteristics.

[0016] In one embodiment, the performing of fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain the fluid dynamics analysis result includes:

[0017] Importing the three-dimensional model into CFD (Computational Fluid Dynamics) software;

[0018] Define the fluid domain of the tank container and set the fluid properties and define boundary conditions based on the type of fluid stored in the tank container to initialize the CFD software;

[0019] The initialized CFD software is used to simulate the internal fluid behavior of the tank container under different pressure and temperature conditions to obtain the fluid dynamics analysis results.

[0020] In one embodiment, performing stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain the stress analysis result includes:

[0021] Importing the three-dimensional model and the fluid dynamics analysis results into FEA (Finite Element Analysis) software;

[0022] Running the FEA software to generate three-dimensional plots, surface plots, xy plots, and tabular values ​​based on the expressions and derived values;

[0023] Based on the three-dimensional plot, surface plot, xy plot and table values, stress analysis results are obtained.

[0024] In one embodiment, the acquiring of the collected real-time data of pressure deformation of the storage tank container, and obtaining the predicted data of pressure deformation of the storage tank container in the next prediction period based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result include:

[0025] Obtain historical data of pressure deformation of storage tank containers within a historical period of time, as well as collected real-time data of pressure deformation of storage tank containers;

[0026] Based on the pressure deformation history data, the fluid dynamics analysis results and the stress analysis results, an initial long short-term memory model is trained to obtain a trained long short-term memory model;

[0027] The real-time pressure deformation data is input into the trained long short-term memory model to obtain the pressure deformation prediction data of the next prediction period of the storage tank container.

[0028] In one embodiment, the training of the initial long short-term memory model based on the pressure deformation history data, the fluid dynamics analysis results and the stress analysis results to obtain the trained long short-term memory model includes:

[0029] Respectively extracting temperature data, deformation data and pressure data from the pressure-deformation historical data;

[0030] Obtaining an initial seasonal model, an initial first long short-term memory model, and an initial second long short-term memory model;

[0031] Training the initial seasonal model according to the temperature data and the fluid dynamics analysis results to obtain a trained seasonal model;

[0032] Training the initial first long short-term memory model according to the deformation data, the fluid dynamics analysis result, and the stress analysis result to obtain a trained first long short-term memory model;

[0033] Training the initial second long short-term memory model according to the pressure data, the fluid dynamics analysis result, and the stress analysis result to obtain a trained second long short-term memory model;

[0034] The step of inputting the real-time pressure deformation data into the trained long short-term memory model to obtain the pressure deformation prediction data of the next prediction period of the storage tank container includes:

[0035] Respectively extracting real-time temperature data, real-time deformation data and real-time pressure data from the pressure-deformation real-time data;

[0036] Inputting the real-time temperature data into the trained seasonal model to obtain temperature forecast data for the next forecast period of the storage tank container;

[0037] Inputting the real-time deformation data into the trained first long short-term memory model to obtain deformation prediction data of the storage tank container in the next prediction period;

[0038] The real-time pressure data is input into the trained second long short-term memory model to obtain the pressure prediction data of the storage tank container in the next prediction period.

[0039] In one embodiment, the above-mentioned storage tank container pressure deformation early warning method further includes:

[0040] Obtaining an initial regression tree model, and the material model and service life of the storage tank container corresponding to the pressure deformation historical data;

[0041] Combining the pressure-deformation historical data with the temperature prediction data, deformation prediction data, and pressure prediction data of the storage tank container in the next prediction period to obtain prediction training data;

[0042] Classify the prediction training data according to the material model and service life of the storage tank container to obtain different types of prediction training data;

[0043] Performing abnormality determination training on the initial regression tree model based on the different types of prediction training data to obtain a trained regression tree model;

[0044] If an abnormality is determined based on the trained regression tree model, a preset alarm message is pushed.

[0045] In a second aspect, the present application also provides a storage tank container pressure deformation warning device. The device comprises:

[0046] A model acquisition module, used to acquire a three-dimensional model of a storage tank container;

[0047] A fluid dynamics analysis module, used to perform a fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain a fluid dynamics analysis result;

[0048] A stress analysis module, used to perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result;

[0049] A prediction module, used to obtain the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the storage tank container in the next prediction period based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result;

[0050] The alarm module is used to push a preset alarm message if an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data.

[0051] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0052] Obtain a 3D model of the tank container;

[0053] Performing fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain fluid dynamics analysis results;

[0054] Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result;

[0055] Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result;

[0056] If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

[0057] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0058] Obtain a 3D model of the tank container;

[0059] Performing fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain fluid dynamics analysis results;

[0060] Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result;

[0061] Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result;

[0062] If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

[0063] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0064] Obtain a 3D model of the tank container;

[0065] Performing fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain fluid dynamics analysis results;

[0066] Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result;

[0067] Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result;

[0068] If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

[0069] The above-mentioned storage tank container pressure deformation warning method, device, computer equipment, storage medium and computer program product obtain the three-dimensional model of the storage tank container; perform fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain the fluid dynamics analysis results; perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis results to obtain the stress analysis results; obtain the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results; if an abnormality is determined based on the real-time data of pressure deformation and the pressure deformation prediction data, a preset alarm message is pushed. In the whole process, the pressure deformation data of the storage tank container is simulated and predicted through the three-dimensional model, fluid dynamics analysis and stress analysis of the storage tank container, and then the simulated prediction data is compared with the real-time collected data to predict abnormal situations that may occur in the future, so as to achieve efficient and accurate pressure deformation warning of the storage tank container. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A diagram showing an application environment of a storage tank container pressure deformation early warning method in one embodiment;

[0071] Figure 2 A schematic diagram of a process of a method for early warning of pressure deformation of a storage tank container in one embodiment;

[0072] Figure 3 A schematic flow chart of a method for early warning of pressure deformation of a storage tank container in another embodiment;

[0073] Figure 4 A schematic diagram of the technical architecture of a long short-term memory model training and prediction application in one embodiment;

[0074] Figure 5 It is a structural block diagram of a storage tank container pressure deformation early warning device in one embodiment;

[0075] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0077] The storage tank container pressure deformation early warning method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 sends an early warning request to the server 104, and the server 104 responds to the request and obtains the three-dimensional model of the storage tank container; based on the three-dimensional model, the fluid in the storage tank container is subjected to fluid dynamics analysis to obtain the fluid dynamics analysis results; according to the three-dimensional model and the fluid dynamics analysis results, the stress analysis of the storage tank container is performed to obtain the stress analysis results; the real-time pressure deformation data of the collected storage tank container is obtained, and based on the real-time pressure deformation data, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results, the pressure deformation prediction data of the next prediction cycle of the storage tank container is obtained; if the pressure deformation real-time data and the pressure deformation prediction data are judged to be abnormal, the preset alarm message is pushed. Further, the server 104 can push the preset alarm information to the handheld terminal of the manager. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0078] In one embodiment, Figure 2As shown, a method for early warning of pressure deformation of a storage tank container is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0079] S100: Acquire a three-dimensional model of a storage tank container.

[0080] In this embodiment, firstly, a precise 3D model of the storage tank container is obtained by using 3D modeling software or 3D reconstruction technology based on point cloud data. The model needs to include all key geometric features of the storage tank container, such as tank shape, wall thickness, inlet and outlet positions and dimensions, etc. To ensure the accuracy of the model, it can be corrected in combination with on-site measurement data.

[0081] S200: Perform fluid dynamics analysis on the fluid in the tank container based on the three-dimensional model to obtain fluid dynamics analysis results.

[0082] Based on the acquired three-dimensional model, fluid dynamics simulation software (such as CFD software) is used to simulate and analyze the fluid in the tank container. During the analysis process, the physical properties of the fluid (such as density, viscosity), initial conditions (such as flow rate, pressure) and boundary conditions (such as wall friction coefficient, heat exchange between fluid and wall, etc.) need to be set. Through simulation, fluid dynamics analysis results such as velocity field and pressure field of the fluid in the tank are obtained. These results help to understand the distribution of the force exerted by the fluid on the wall of the tank container.

[0083] S300: Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis results to obtain stress analysis results.

[0084] Combine the results of fluid dynamics analysis with the three-dimensional model, and use finite element analysis (FEA) or similar technology to perform stress analysis on the tank container. In the analysis, it is necessary to consider the effects of fluid pressure, temperature gradient, material properties (such as elastic modulus, Poisson's ratio) and other factors on the wall stress of the tank container. Through calculation, the stress distribution diagram of the tank container under specific working conditions and possible stress concentration areas are obtained.

[0085] S400: Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results.

[0086] The storage tank container is equipped with pressure sensors and deformation monitoring equipment (such as strain gauges, laser rangefinders, etc.). These devices collect real-time pressure deformation data of the storage tank container and send the real-time collected data to the server. The server receives the real-time pressure deformation data of the storage tank container and can pre-process these data, such as filtering and denoising, to improve the accuracy and reliability of the data. At the same time, the real-time data is associated with the three-dimensional model, fluid dynamics analysis results and stress analysis results to provide a basis for subsequent predictive analysis. Further, the real-time pressure deformation data includes three categories: real-time temperature data, real-time deformation data and real-time pressure data. These three types of data can be collected by different sensing and monitoring equipment.

[0087] S500: If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

[0088] Based on the collected real-time data of pressure deformation, three-dimensional models, fluid dynamics analysis results and stress analysis results, a prediction model for pressure deformation of storage tank containers is established using machine learning algorithms (such as time series analysis, neural networks, etc.) or physical models (such as elastic mechanics models, fluid-solid coupling models, etc.). Through this model, the pressure deformation of the storage tank container in the next prediction period is predicted. The prediction results should include the size, direction and possible danger areas of the deformation. Compare the prediction results with the preset safety threshold. If the prediction results show that the pressure deformation of the storage tank container exceeds the safety threshold, or the deformation trend is abnormal (such as a sharp increase, sudden change, etc.), it is judged to be abnormal. At this time, the server automatically triggers the alarm mechanism and pushes the preset alarm message to the relevant personnel. The alarm message should contain specific information of the abnormality (such as deformation size, location, possible hazards, etc.) and emergency handling suggestions.

[0089] The above-mentioned pressure deformation warning method for storage tank containers obtains a three-dimensional model of the storage tank container; performs fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain the fluid dynamics analysis results; performs stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis results to obtain the stress analysis results; obtains the collected real-time data of pressure deformation of the storage tank container, and obtains the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results; if an abnormality is determined based on the real-time data of pressure deformation and the pressure deformation prediction data, a preset alarm message is pushed. In the whole process, the pressure deformation data of the storage tank container is simulated and predicted through the three-dimensional model, fluid dynamics analysis and stress analysis of the storage tank container, and then the simulated prediction data is compared with the real-time collected data to predict abnormal situations that may occur in the future, so as to achieve efficient and accurate pressure deformation warning of the storage tank container.

[0090] To go further, the specific calculation steps of deformation real-time data are as follows: The volume calculation method based on the center of gravity is a technology that uses the geometric characteristics of point cloud data to estimate the volume. The core idea of ​​this method is to calculate the center of mass (center of gravity) of the point cloud, and then use the center of mass coordinates to estimate the volume of the object represented by the entire point cloud.

[0091] The following is a detailed description of the method:

[0092] 1. Point cloud centroid calculation:

[0093] First, calculate the centroid coordinates of the point cloud by averaging the coordinates of all points in the point cloud. The calculation formula is:

[0094] Among them, (x i ,y i , z i ) is the coordinate of the i-th point in the point cloud, and n is the total number of points in the point cloud.

[0095] 2. Point cloud rotation transformation:

[0096] Calculate the eigenvalues ​​and eigenvectors of the point cloud, and perform a rotation transformation on the point cloud so that the center of mass of the point cloud moves to the origin of the coordinate system.

[0097] 3. Volume estimation:

[0098] The point cloud data is divided into multiple small volume units, and then the volume of each unit is calculated, and finally the volume of all units is added up to get the total volume. For example, if the point cloud is approximated to an ellipsoid, the volume formula of the ellipsoid is used to estimate the volume:

[0099]

[0100] abc is the semi-axis length of the ellipsoid, which can be estimated by the standard deviation of the point cloud data.

[0101] 4. Rotation and center of mass recovery:

[0102] After completing the volume estimation, the point cloud needs to be rotated back to its original pose and the center of mass coordinates restored to maintain the original spatial relationship of the point cloud data.

[0103] The volume calculation method based on the center of gravity is applicable to various shapes and provides a more accurate volume estimation, especially when the point cloud data is dense and evenly distributed. In one embodiment, obtaining a three-dimensional model of a tank container includes:

[0104] Step 1: Obtain 3D scanning data of the tank container.

[0105] Use 3D scanning equipment (such as laser scanner, structured light scanner, etc.) to scan the tank container in all directions to obtain the 3D point cloud data of its surface. During the scanning process, it is necessary to ensure the scanning accuracy and coverage to obtain the complete geometric shape information of the tank container.

[0106] Step 2: Based on the 3D scanning data, extract the geometric shape characteristics, material property characteristics and internal structure characteristics of the storage tank container.

[0107] Based on the acquired 3D scanning data, point cloud processing software or algorithms are used to extract the geometric shape features of the storage tank container, such as tank size, wall thickness, inlet and outlet locations and sizes, etc. At the same time, the server can query existing on-site surveys or related information to obtain the material property characteristics of the storage tank container, such as material type, elastic modulus, Poisson's ratio, etc. For internal structural features, such as internal support structures, partitions, heating / cooling elements, etc., they can be extracted through internal slices of the scanned data or combined with the design drawings of the storage tank container.

[0108] Step 3: Construct a three-dimensional model of the tank container based on the geometric shape characteristics, material property characteristics and internal structure characteristics.

[0109] Based on the extracted geometric shape features, material property features and internal structure features, use 3D modeling software (such as SolidWorks, AutoCAD, etc.) or 3D reconstruction algorithms to build an accurate 3D model of the tank container. The model must contain all key geometric features, material properties and internal structures to ensure the accuracy of subsequent analysis.

[0110] In one embodiment, if Figure 3 As shown, S200 includes:

[0111] S220: Import the three-dimensional model into CFD software.

[0112] Use professional CFD software (such as ANSYS Fluent, CFX, STAR-CCM+, etc.) to import the previously constructed 3D model of the tank container into the software. Ensure the accuracy and completeness of the geometric shape during the model import process.

[0113] S240: Define the fluid domain of the storage tank container, and set the fluid properties and define boundary conditions based on the type of fluid stored in the storage tank container to initialize the CFD software.

[0114] In CFD software, the fluid domain is defined according to the actual structure of the tank container and the area where the fluid is stored. The fluid domain is the spatial area occupied by the fluid during the simulation process. According to the type of fluid actually stored in the tank container (such as oil, natural gas, water, etc.), the corresponding fluid properties are set in the CFD software, including density, viscosity, specific heat capacity, etc. These properties have an important impact on the results of fluid dynamics analysis. Boundary conditions are physical conditions on the boundaries of the fluid domain during the simulation process. In CFD software, boundary conditions such as inlet velocity, outlet pressure, wall temperature, etc. are defined according to the actual situation of the tank container and the simulation requirements. These conditions will directly affect the flow state of the fluid in the tank container. After setting the fluid properties and boundary conditions, initialize the CFD software. The initialization process includes meshing, solver selection, time step setting, etc. Meshing is to discretize the fluid domain into a series of interconnected units for numerical solution. The solver selection depends on the specific problem and fluid properties of the simulation. The time step setting determines the step size of time advancement during the simulation process.

[0115] S260: The initialized CFD software is used to simulate the internal fluid behavior of the tank container under different pressure and temperature conditions to obtain the fluid dynamics analysis results.

[0116] Use the initialized CFD software to simulate the internal fluid behavior of the tank container under different pressure and temperature conditions. During the simulation process, the CFD software will calculate the flow state, velocity distribution, pressure distribution, etc. of the fluid in the tank container based on the principles of fluid dynamics (such as conservation of mass, momentum, energy, etc.) and the set fluid properties and boundary conditions. After the simulation is completed, the fluid dynamics analysis results are exported from the CFD software. These results usually include the velocity field, pressure field, temperature field, etc. of the fluid in the tank container, as well as the force distribution of the fluid on the wall of the tank container. These results will provide an important basis for subsequent stress analysis and deformation prediction.

[0117] In one embodiment, if Figure 3 As shown, S300 includes:

[0118] S320: Import the 3D model and fluid dynamics analysis results into FEA software.

[0119] After completing the fluid dynamics analysis, the three-dimensional model including the tank container geometry, fluid domain, fluid properties and boundary conditions, as well as the fluid dynamics analysis results (such as the force distribution of the fluid on the tank container wall) are imported into the finite element analysis (FEA) software to ensure the accuracy and completeness of the data during the import process.

[0120] S340: Run FEA software to generate 3D plots, surface plots, xy plots, and tabular values ​​based on expressions and derived values.

[0121] In FEA software, finite element meshing is performed on the tank container according to the material properties of the tank container (such as elastic modulus, Poisson's ratio, etc.) and the fluid force distribution in the fluid dynamics analysis results. Then, based on the finite element method, the FEA software is run to calculate the stress distribution of the tank container under the fluid force. During the operation of the FEA software, a series of visual outputs will be generated based on the calculation results, including three-dimensional drawings (displaying the overall stress distribution of the tank container), surface drawings (displaying the stress distribution of the tank container wall or a specific section), xy drawings (displaying the curve of stress variation with position) and table values ​​(listing the stress values ​​of key points). These outputs provide an intuitive and quantitative basis for subsequent stress analysis results.

[0122] S360: Get stress analysis results from 3D plots, surface plots, xy plots, and tabular values.

[0123] By analyzing the 3D plots, surface plots, xy plots, and table values ​​generated by FEA software, you can intuitively understand the stress distribution of the tank container under the action of fluid force. In particular, you can pay attention to information such as stress concentration areas, maximum stress values ​​and their locations, and obtain stress analysis results.

[0124] In one embodiment, obtaining the collected real-time data of pressure deformation of the storage tank container, and obtaining the predicted data of pressure deformation of the storage tank container in the next prediction period based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results includes:

[0125] Step 1: Obtain historical data of pressure deformation of the storage tank container within a historical time period, and collected real-time data of pressure deformation of the storage tank container.

[0126] Extract pressure deformation data in the historical time period from the monitoring system of the storage tank container. These data usually include pressure values ​​and corresponding deformation values ​​at different time points, which are used to analyze the long-term behavior patterns and trends of the storage tank container. The pressure and deformation values ​​of the storage tank container are collected in real time through sensors or other monitoring equipment installed on the storage tank container. These data reflect the current operating status and potential risks of the storage tank container.

[0127] Step 2: Based on the pressure deformation history data, fluid dynamics analysis results, and stress analysis results, an initial long short-term memory model is trained to obtain a trained long short-term memory model.

[0128] The historical data of pressure deformation in the historical time period are preprocessed, including data cleaning, missing value processing, outlier detection, etc., to ensure the accuracy and reliability of the data. According to the results of fluid dynamics analysis and stress analysis, characteristic variables related to pressure deformation, such as fluid force, stress distribution, material properties, etc., are extracted. These characteristic variables will be used as input features of the long short-term memory model. The long short-term memory network (LSTM) is selected as the prediction model because it can handle long-term dependencies in time series data. The initial long short-term memory model is trained using the preprocessed historical data and the extracted characteristic variables. During the training process, the prediction accuracy and generalization ability of the model are improved by adjusting the model parameters and optimizing the algorithm. After multiple iterations of training, the trained long short-term memory model is obtained. The model can predict the pressure deformation of the storage tank container in the future based on the input characteristic variables.

[0129] Step 3: Input the real-time pressure deformation data into the trained long short-term memory model to obtain the pressure deformation prediction data of the tank container in the next prediction period.

[0130] The collected real-time data of pressure deformation of the storage tank container is input into the trained long short-term memory model. These data will be used as the input features of the model to predict the pressure deformation of the next prediction period. The trained long short-term memory model calculates and outputs the predicted data of pressure deformation of the storage tank container for the next prediction period based on the input real-time data of pressure deformation and the extracted characteristic variables. These data include the predicted pressure value and the corresponding deformation value, which are used to evaluate the safety and potential risks of the storage tank container. Specifically, the next prediction period can be set according to the needs of the actual situation, for example, it can be set to 1 day, 3 days, 5 days, etc. In practical applications, the length of the next prediction period can be reasonably selected in combination with the length of the historical time period, and the historical time period + the next prediction period can be used as a large warning period to achieve orderly and accurate warning. For example, 12 consecutive days can be used as a large warning period, the data of the previous 9 days can be used as the historical deformation real-time data, and the pressure deformation prediction data of the next 3 days can be predicted by the data of the previous 9 days.

[0131] In one embodiment, based on the pressure deformation history data, the fluid dynamics analysis results and the stress analysis results, the initial long short-term memory model is trained, and the trained long short-term memory model is obtained, including:

[0132] Step 1: Extract temperature data, deformation data and pressure data from pressure-deformation history data respectively.

[0133] Temperature data, deformation data and pressure data are extracted from the pressure deformation history data. These data will be used to train different long-term and short-term memory models.

[0134] Step 2: Obtain an initial seasonal model, an initial first long short-term memory model, and an initial second long short-term memory model.

[0135] Prepare three initial LSTM models: the first initial LSTM model, the initial first LSTM model and the initial second LSTM model. These models will be used for the prediction of temperature, deformation and pressure respectively.

[0136] Step 3: Train the initial seasonal model based on the temperature data and the results of the fluid dynamics analysis to obtain a trained seasonal model.

[0137] Step 4: Train the initial first long short-term memory model according to the deformation data, the fluid dynamics analysis results, and the stress analysis results to obtain a trained first long short-term memory model.

[0138] Step 5: Train the initial second long short-term memory model according to the pressure data, the fluid dynamics analysis results, and the stress analysis results to obtain a trained second long short-term memory model.

[0139] According to the temperature data and the results of fluid dynamics analysis (such as the effect of fluid temperature on the container wall, etc.), the initial seasonal model is trained to obtain the trained seasonal model. This model can predict the temperature changes of the storage tank container in the future. According to the deformation data, fluid dynamics analysis results and stress analysis results (such as the direct effect of fluid pressure on the deformation of the container wall, the effect of stress distribution on deformation, etc.), the initial first long short-term memory model is trained to obtain the trained first long short-term memory model. This model can predict the deformation of the storage tank container in the future. According to the pressure data, fluid dynamics analysis results and stress analysis results (such as the change trend of fluid pressure, the effect of stress concentration area on pressure bearing capacity, etc.), the initial second long short-term memory model is trained to obtain the trained second long short-term memory model. This model can predict the pressure changes of the storage tank container in the future. Specifically, the seasonal model is a type of sparse coefficient ARIMA model, which is used to describe the obvious periodicity in the time series, which is usually caused by seasonal changes.

[0140] The real-time pressure deformation data is input into the trained long short-term memory model to obtain the pressure deformation prediction data of the tank container in the next prediction period, including:

[0141] Step 1: respectively extract the real-time temperature data, real-time deformation data and real-time pressure data from the pressure deformation real-time data.

[0142] Real-time temperature data, real-time deformation data and real-time pressure data are extracted from the real-time pressure deformation data. These data will be used as inputs of the trained long short-term memory model.

[0143] Step 2: Input the real-time temperature data into the trained seasonal model to obtain the temperature forecast data of the tank container in the next forecast period;

[0144] Step 3: Input the real-time deformation data into the first trained long short-term memory model to obtain the deformation prediction data of the storage tank container in the next prediction period;

[0145] Step 4: Input the real-time pressure data into the trained second long short-term memory model to obtain the pressure prediction data of the tank container for the next prediction period.

[0146] Input the real-time temperature data into the trained seasonal model to obtain the temperature prediction data of the next prediction period of the storage tank container. Input the real-time deformation data into the trained first long short-term memory model to obtain the deformation prediction data of the next prediction period of the storage tank container. This prediction data reflects the deformation trend and possible risk points of the storage tank container during the prediction period. Input the real-time pressure data into the trained second long short-term memory model to obtain the pressure prediction data of the next prediction period of the storage tank container. This prediction data helps to evaluate the pressure bearing capacity and potential safety risks of the storage tank container during the prediction period.

[0147] In one embodiment, the above-mentioned storage tank container pressure deformation early warning method further includes:

[0148] Step 1: Obtain an initial regression tree model, and the material model and service life of the storage tank container corresponding to the pressure deformation historical data.

[0149] First, obtain an initial regression tree model. This model will be used to determine abnormalities in the predicted data. At the same time, collect the material model and service life of the tank container corresponding to the pressure deformation history data. This information is crucial to understanding the physical properties and aging of the tank container, as they may affect the deformation behavior of the tank container.

[0150] Step 2: Combine the pressure-deformation historical data with the temperature prediction data, deformation prediction data and pressure prediction data of the next prediction period of the storage tank container to obtain prediction training data.

[0151] The pressure deformation history data is combined with the temperature prediction data, deformation prediction data and pressure prediction data of the next prediction period of the storage tank container to form a comprehensive data set. This data set contains various parameter information of the storage tank container in the past and in the future, and is the basis for training the regression tree model. For example, the pressure deformation history data of 6 days in the historical records can be combined with the predicted temperature prediction data, deformation prediction data and pressure prediction data of the next 3 days to form a comprehensive prediction training data set.

[0152] Step 3: Classify the prediction training data according to the material model and service life of the storage tank container to obtain different types of prediction training data.

[0153] The combined prediction training data is divided into types according to the material model and service life of the tank container. This means that the tank container data with similar materials and service life are classified into one category to train the regression tree model more accurately. Type division helps the model learn the deformation patterns unique to different tank container types.

[0154] Step 4: Perform abnormality determination training on the initial regression tree model based on the different types of prediction training data to obtain a trained regression tree model.

[0155] The initial regression tree model is trained using different types of prediction training data. During the training process, the model will learn how to determine whether there is an abnormal deformation risk based on various parameter information of the tank container (including historical deformation data, prediction data, material model, and service life). After the training is completed, a trained regression tree model is obtained. This model can predict whether the tank container is in an abnormal state based on the input data.

[0156] Step 6: If an abnormality is determined based on the trained regression tree model, a preset alarm message is pushed.

[0157] In actual applications, the real-time collected tank container data (including temperature, deformation, pressure, etc.) is input into the trained regression tree model to obtain the temperature prediction data, deformation prediction data and pressure prediction data for the next prediction period. Then, these prediction data are input into the trained regression tree model together with the material model and service life of the tank container. If the regression tree model determines that there is an abnormal deformation risk (that is, the data exceeds the normal deformation range learned by the model), the system will automatically push the preset alarm message. This alarm message can contain detailed information about the abnormal situation so that the operator can take timely measures.

[0158] Specifically, a regression tree is a decision tree whose leaf nodes contain a predicted value, which is usually the average value of a target variable for the sample represented by the node. The regression tree model can be used to predict continuous numerical data. The following are the key points and construction process of the regression tree model:

[0159] 1. Select the best split point: Starting from the root node, select a threshold to split the data so that the mean square error of the split child nodes is minimized.

[0160] 2. Recursive splitting: Repeat the first step for each child node until the stopping condition is met, such as the number of samples contained in the node is less than a certain threshold.

[0161] 3. Stopping conditions: Determine when to stop growing the tree to avoid overfitting. Common stopping conditions include the tree reaching the maximum depth, the amount of data in the node is less than a certain threshold, or the reduction of the mean square error is no longer significant.

[0162] 4. Construct leaf nodes: At each leaf node of the tree, calculate the average value of the target variable of the samples contained in the node as the predicted value of the node.

[0163] 5. Pruning: Prune the generated tree to avoid overfitting.

[0164] 6. Dealing with missing values: In the process of building a tree, you need to consider how to deal with missing values ​​in the data.

[0165] The regression tree model finally obtained can process various types of data, categorical and continuous variables. It can be classified according to different material models, and then output the relevant data of how many days of deformation warning (days, deformation value, warning) according to various influencing factors.

[0166] In simple terms, the seasonal model, the first long short-term memory model, the second long short-term memory model and the regression tree model can be regarded as an overall large model. The large model mainly includes two layers. The first layer has three sub-models, namely the seasonal model, the first long short-term memory model and the second long short-term memory model, which respectively realize the prediction of temperature, deformation and pressure. The second layer has a regression model, which realizes the early warning of the pressure deformation of the storage tank container based on the predicted data and the real-time data. The whole large model can be trained with a unified loss function, and its total loss function loss 总 =loss1+loss2+loss3+loss 回 Among them, loss1 is the loss function corresponding to the seasonal model; loss2 is the loss function corresponding to the first long short-term memory model; loss3 is the loss function corresponding to the second long short-term memory model; loss 回 is the loss function corresponding to the regression model.

[0167] In practical applications, the long-term and short-term memory model training and prediction application process of temperature, deformation and pressure are carried out separately. Figure 4 shown.

[0168] Overall, this comprehensive solution can not only provide early warning of potential tank failure risks, but also optimize operating conditions, extend equipment life, and ensure industrial safety and efficiency. The application of the tank container pressure deformation early warning method of this application in practical applications has the following significant technical effects:

[0169] 1) Improve the safety performance of storage tanks: By real-time monitoring of the pressure and deformation of storage tanks, potential safety hazards can be discovered in time to avoid accidents caused by pressure and deformation.

[0170] 2) Reduce maintenance costs: Regular inspection and maintenance of storage tanks requires a lot of time, manpower and material resources, and the use of early warning methods based on 3D modeling can reduce the number of maintenance times and costs.

[0171] 3) Increase production efficiency: By timely warning and handling of tank problems, production interruptions and losses caused by tank failures can be avoided, and production efficiency and economic benefits can be improved.

[0172] 4) Sustainable development: The use of early warning methods based on 3D modeling can improve the reliability and safety of storage tanks, meet the requirements of sustainable development, and be beneficial to protecting the environment and human health.

[0173] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0174] Based on the same inventive concept, the embodiment of the present application also provides a storage tank container pressure deformation warning device for implementing the above-mentioned storage tank container pressure deformation warning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more storage tank container pressure deformation warning device embodiments provided below can refer to the limitations of the storage tank container pressure deformation warning method above, and will not be repeated here.

[0175] In one embodiment, Figure 5 As shown, a storage tank container pressure deformation early warning device is provided, comprising:

[0176] The model acquisition module 100 is used to acquire a three-dimensional model of the storage tank container;

[0177] A fluid dynamics analysis module 200 is used to perform a fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain a fluid dynamics analysis result;

[0178] The stress analysis module 300 is used to perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis results to obtain the stress analysis results;

[0179] The prediction module 400 is used to obtain the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the storage tank container in the next prediction period based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis results and the stress analysis results;

[0180] The alarm module 500 is used to push a preset alarm message if an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data.

[0181] In one embodiment, the model acquisition module 100 is also used to acquire three-dimensional scanning data of the storage tank container; based on the three-dimensional scanning data, extract the geometric shape characteristics, material property characteristics and internal structure characteristics of the storage tank container; and construct a three-dimensional model of the storage tank container according to the geometric shape characteristics, material property characteristics and internal structure characteristics.

[0182] In one embodiment, the fluid dynamics analysis module 200 is also used to import the three-dimensional model into the CFD software; define the fluid domain of the tank container, and set the fluid properties and define boundary conditions based on the type of fluid stored in the tank container to initialize the CFD software; through the initialized CFD software, simulate the internal fluid behavior of the tank container under different pressure and temperature conditions to obtain the fluid dynamics analysis results.

[0183] In one embodiment, the stress analysis module 300 is also used to import the three-dimensional model and fluid dynamics analysis results into FEA software; run the FEA software to generate three-dimensional plots, surface plots, xy plots and table values ​​based on expressions and derived values; and obtain stress analysis results based on the three-dimensional plots, surface plots, xy plots and table values.

[0184] In one embodiment, the prediction module 400 is also used to obtain historical data of pressure deformation of the storage tank container within a historical time period, and collected real-time data of pressure deformation of the storage tank container; based on the historical data of pressure deformation, fluid dynamics analysis results and stress analysis results, train an initial long-short-term memory model to obtain a trained long-short-term memory model; input the real-time pressure deformation data into the trained long-short-term memory model to obtain the pressure deformation prediction data of the storage tank container in the next prediction period.

[0185] In one embodiment, the prediction module 400 is also used to extract temperature data, deformation data and pressure data from the pressure deformation historical data respectively; obtain an initial seasonal model, an initial first long short-term memory model and an initial second long short-term memory model; train the initial seasonal model according to the temperature data and the fluid dynamics analysis results to obtain a trained seasonal model; train the initial first long short-term memory model according to the deformation data, the fluid dynamics analysis results and the stress analysis results to obtain a trained first long short-term memory model; train the initial second long short-term memory model according to the pressure data, the fluid dynamics analysis results and the stress analysis results to obtain a trained second long short-term memory model; extract real-time temperature data, real-time deformation data and real-time pressure data from the pressure deformation real-time data respectively; input the real-time temperature data into the trained seasonal model to obtain the temperature prediction data of the next prediction period of the storage tank container; input the real-time deformation data into the trained first long short-term memory model to obtain the deformation prediction data of the next prediction period of the storage tank container; input the real-time pressure data into the trained second long short-term memory model to obtain the pressure prediction data of the next prediction period of the storage tank container.

[0186] In one of the embodiments, the prediction module 400 is also used to obtain an initial regression tree model, and the material model and service life of the tank container corresponding to the pressure deformation history data; combine the pressure deformation history data and the temperature prediction data, deformation prediction data and pressure prediction data of the next prediction period of the tank container to obtain prediction training data; classify the prediction training data according to the material model and service life of the tank container to obtain different types of prediction training data; perform abnormality judgment training on the initial regression tree model based on different types of prediction training data to obtain a trained regression tree model; the alarm module 500 is also used to push a preset alarm message if an abnormality is judged based on the trained regression tree model.

[0187] Each module in the above-mentioned storage tank container pressure deformation warning device can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

[0188] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. 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 preset data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a pressure deformation early warning method for a storage tank container is implemented.

[0189] Those skilled in the art will understand that Figure 6 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.

[0190] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned storage tank container pressure deformation early warning method when executing the computer program.

[0191] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned storage tank container pressure deformation early warning method is implemented.

[0192] In one embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned storage tank container pressure deformation early warning method when executed by a processor.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0194] 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.

[0195] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for early warning of pressure deformation of a storage tank container, characterized in that: The method comprises: Obtain a 3D model of the tank container; Performing fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain fluid dynamics analysis results; Perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result; Acquire the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the next prediction period of the storage tank container based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result; If an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data, a preset alarm message is pushed.

2. The method according to claim 1, characterized in that The step of obtaining the three-dimensional model of the storage tank container comprises: Obtain 3D scanning data of storage tank containers; Extracting geometric shape features, material property features, and internal structure features of the storage tank container based on the three-dimensional scanning data; A three-dimensional model of the storage tank container is constructed according to the geometric shape characteristics, the material property characteristics and the internal structure characteristics.

3. The method according to claim 1, characterized in that The fluid dynamics analysis of the fluid in the storage tank container based on the three-dimensional model to obtain the fluid dynamics analysis results includes: Importing the three-dimensional model into CFD software; Define the fluid domain of the tank container and set the fluid properties and define boundary conditions based on the type of fluid stored in the tank container to initialize the CFD software; The initialized CFD software is used to simulate the internal fluid behavior of the tank container under different pressure and temperature conditions to obtain the fluid dynamics analysis results.

4. The method according to claim 1, characterized in that: The stress analysis of the storage tank container is performed according to the three-dimensional model and the fluid dynamics analysis result to obtain the stress analysis result, which includes: Importing the three-dimensional model and the fluid dynamics analysis results into FEA software; Running the FEA software to generate three-dimensional plots, surface plots, xy plots, and tabular values ​​based on the expressions and derived values; Based on the three-dimensional plot, surface plot, xy plot and table values, stress analysis results are obtained.

5. The method according to claim 1, characterized in that The acquiring of the collected real-time pressure deformation data of the storage tank container, and obtaining the pressure deformation prediction data of the storage tank container in the next prediction period based on the real-time pressure deformation data, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result include: Obtain historical data of pressure deformation of storage tank containers within a historical period of time, as well as collected real-time data of pressure deformation of storage tank containers; Based on the pressure deformation history data, the fluid dynamics analysis results and the stress analysis results, an initial long short-term memory model is trained to obtain a trained long short-term memory model; The real-time pressure deformation data is input into the trained long short-term memory model to obtain the pressure deformation prediction data of the next prediction period of the storage tank container.

6. The method according to claim 5, characterized in that The training of the initial long short-term memory model based on the pressure deformation history data, the fluid dynamics analysis result and the stress analysis result to obtain the trained long short-term memory model includes: Respectively extracting temperature data, deformation data and pressure data from the pressure-deformation historical data; Obtaining an initial seasonal model, an initial first long short-term memory model, and an initial second long short-term memory model; Training the initial seasonal model according to the temperature data and the fluid dynamics analysis results to obtain a trained seasonal model; Training the initial first long short-term memory model according to the deformation data, the fluid dynamics analysis result, and the stress analysis result to obtain a trained first long short-term memory model; Training the initial second long short-term memory model according to the pressure data, the fluid dynamics analysis result, and the stress analysis result to obtain a trained second long short-term memory model; The step of inputting the real-time pressure deformation data into the trained long short-term memory model to obtain the pressure deformation prediction data of the next prediction period of the storage tank container includes: Respectively extracting real-time temperature data, real-time deformation data and real-time pressure data from the pressure-deformation real-time data; Inputting the real-time temperature data into the trained seasonal model to obtain temperature forecast data for the next forecast period of the storage tank container; Inputting the real-time deformation data into the trained first long short-term memory model to obtain deformation prediction data of the storage tank container in the next prediction period; The real-time pressure data is input into the trained second long short-term memory model to obtain the pressure prediction data of the storage tank container in the next prediction period.

7. The method according to claim 6, characterized in that Also includes: Obtaining an initial regression tree model, and the material model and service life of the storage tank container corresponding to the pressure deformation historical data; Combining the pressure-deformation historical data with the temperature prediction data, deformation prediction data, and pressure prediction data of the storage tank container in the next prediction period to obtain prediction training data; Classify the prediction training data according to the material model and service life of the storage tank container to obtain different types of prediction training data; Performing abnormality determination training on the initial regression tree model based on the different types of prediction training data to obtain a trained regression tree model; If an abnormality is determined based on the trained regression tree model, a preset alarm message is pushed.

8. A pressure deformation warning device for a storage tank container, characterized in that: The device comprises: A model acquisition module, used to acquire a three-dimensional model of a storage tank container; A fluid dynamics analysis module, used to perform a fluid dynamics analysis on the fluid in the storage tank container based on the three-dimensional model to obtain a fluid dynamics analysis result; A stress analysis module, used to perform stress analysis on the storage tank container according to the three-dimensional model and the fluid dynamics analysis result to obtain a stress analysis result; A prediction module, used to obtain the collected real-time data of pressure deformation of the storage tank container, and obtain the pressure deformation prediction data of the storage tank container in the next prediction period based on the real-time data of pressure deformation, the three-dimensional model, the fluid dynamics analysis result and the stress analysis result; The alarm module is used to push a preset alarm message if an abnormality is determined based on the pressure deformation real-time data and the pressure deformation prediction data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images