Jacket type platform fatigue life online prediction method and system based on digital twinning

Abstract

The invention provides a jacket type platform fatigue life online prediction method and system based on digital twinning, and relates to the technical field of ocean engineering equipment. The jacket type platform fatigue life online prediction method comprises the steps that historical stress test data, material property data, stress data and environment data of jacket type platform materials are collected; the method comprises the following steps: constructing an ideal fatigue life prediction model, obtaining strain stress through stress data, inputting the strain stress into the ideal fatigue life prediction model to obtain ideal fatigue life, and correcting the ideal fatigue life by using environmental data to obtain corrected fatigue life. The material property data and the stress data of the jacket type platform are analyzed to obtain fatigue damage, and the fatigue damage is used for conducting secondary correction on the corrected fatigue life to obtain the actual fatigue life; a digital twin platform is constructed, and high-precision real-time mapping of a jacket type platform physical model and a digital model is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of marine engineering equipment, and in particular to an online prediction method and system for fatigue life of a jacket-type platform based on digital twins. Background Art

[0002] In the field of offshore oil and gas extraction, jacket platforms are widely used due to their stable structure and strong adaptability. However, such platforms are in the marine environment for a long time and are affected by dynamic environmental factors such as waves, tides, and wind loads, and their structures are subjected to complex stresses. Stress fluctuations and corrosion in this environment will gradually cause fatigue damage to the material, thereby reducing the structural strength and service life of the platform. Therefore, accurately predicting the fatigue life of jacket platforms is of great significance to ensuring the safety of offshore operations and extending the service life of the platform.

[0003] Traditional fatigue life prediction methods mainly rely on linear regression of historical data, statistical models or accelerated fatigue tests in the laboratory. Although these methods can provide fatigue life estimates to a certain extent, they generally have problems such as poor real-time performance, inability to dynamically reflect the state of the structure in actual complex environments, and insufficient consideration of environmental impacts. These deficiencies make it difficult to timely discover and deal with potential structural problems during platform operations, posing a major safety hazard. Therefore, there is an urgent need for a fatigue life prediction method that can comprehensively consider the actual working environment, material properties and real-time stress state to improve the safety and operational efficiency of the platform.

[0004] Digital twin technology has been widely used in various industrial fields in recent years. It can reflect the state and behavior of physical systems in real time through the close combination of virtual and reality. Applying digital twin technology to the fatigue life prediction of jacket-type platforms can achieve accurate monitoring and prediction of the actual operating status of the platform, providing a new way to timely discover and respond to structural fatigue damage.

[0005] In the prior art, application number CN116992733A discloses an online prediction method for fatigue life of a jacket structure based on digital twin, which includes: establishing a three-dimensional model of the jacket; performing dynamic simulation analysis on the three-dimensional model of the jacket, importing a period of wind and wave load time history data as environmental load input, and setting boundary conditions to obtain a finite element model of the jacket; using finite element software to analyze the dynamic response and fatigue characteristics of the jacket structure and establish a dynamic response data set and a fatigue life data set; using model reduction technology to construct a dynamic reduced-order model of the jacket; using a long short-term memory neural network algorithm to construct a fatigue life prediction model based on time series; and establishing a digital twin monitoring system for fatigue life of the jacket structure. This prior art can establish a digital twin model for a real jacket-type platform structure, realize real-time online accurate prediction of the fatigue life of the jacket structure, and effectively improve the timeliness and accuracy of fatigue life prediction. However, the existing technology still has defects. The existing technology only considers the stress and strain data during the wind and wave process, but ignores the impact of the marine environment on the fatigue life of the jacket platform, which will lead to an incomplete assessment of the fatigue life; secondly, the fatigue life of the material will be reduced by the stress. The existing technology only takes one set of data for life prediction and ignores the impact of the previous stress on the fatigue life of the material, which will make the prediction result lack accuracy and reliability.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The object of the present invention is to provide a method and system for online prediction of fatigue life of a jacket-type platform based on digital twin, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] An online prediction method for fatigue life of a jacket platform based on digital twin, the specific steps include:

[0010] Step 1: Collect historical stress test data of jacket platform materials, material property data, stress data and environmental data of jacket platform; the historical stress test data includes test stress magnitude and test fatigue life; the jacket platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity;

[0011] Step 2: The historical stress magnitudes are used to form a data set, and an ideal fatigue life prediction model is constructed using the test fatigue life as a label. The ideal fatigue life prediction model is trained and optimized using the data set to obtain the ideal fatigue life prediction model after training.

[0012] Step 3: Extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on environmental data to generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life;

[0013] Step 4: Perform damage analysis on stress data to calculate cumulative stress damage, obtain material fatigue resistance based on material property data of jacket-type platform, generate fatigue damage based on cumulative stress damage and material fatigue resistance; perform secondary correction on corrected fatigue life through fatigue damage to obtain actual fatigue life;

[0014] Step 5: Build a digital twin platform, transmit the stress data and environmental data of the jacket platform to the digital twin platform of the jacket platform to build a digital model of the jacket platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket platform.

[0015] Furthermore, the specific logic for extracting strain and stress is: calculate the average stress value between each stress maximum and the adjacent minimum, and perform weighted mean operation on the average stress value to obtain the strain and stress; the specific formula for calculating the average stress value is:

[0016]

[0017] in, is the average stress value, T is the total time of the time series data, and F(t) is the stress time series data;

[0018] The specific logic for obtaining strain stress is:

[0019]

[0020] Where Ff is strain stress, t i is the time interval corresponding to the i-th average stress value, is the i average stress value, and n is the number of average stress values ​​in the stress time series data.

[0021] Furthermore, the specific logic for generating the corrected fatigue life is as follows: input strain stress into the optimized ideal fatigue life prediction model ideal fatigue life, perform mathematical analysis on environmental data, generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate the corrected fatigue life; the specific formula for generating the environmental correction factors is as follows:

[0022] A=W(PH-7) 2 tan -1 C O *C Y

[0023] Among them, A is the environmental correction factor, W is the temperature, PH is the pH value of seawater, C o is the dissolved oxygen content, C Y is salinity;

[0024] The specific formula based on which the corrected fatigue life is generated is:

[0025]

[0026] Among them, TD is the corrected fatigue life and Td is the ideal fatigue life.

[0027] Furthermore, the specific logic for generating stress damage is: threshold processing is performed on stress data through fatigue limit, the stress data is transformed into effective stress data, and stress damage is generated on the effective stress data; the specific logic for generating effective stress data is:

[0028]

[0029] Among them, F i ′ is the effective stress data, F i is stress data, F O is the fatigue limit;

[0030] The specific formula for generating stress damage is:

[0031]

[0032] Where Hu is stress damage, F′ i (t) is the effective stress time series data, and L is the length of the time series data.

[0033] Furthermore, the specific logic for generating fatigue damage is: obtaining material fatigue resistance according to the material property data of the jacket platform, and generating fatigue damage according to the accumulated stress damage and material fatigue resistance; the specific logic for generating material fatigue resistance is:

[0034] K=F O *R*e Hi

[0035] Among them, K is the material fatigue resistance, F O is the fatigue limit, R is the toughness, and Hi is the corrosion resistance of the coating;

[0036] The specific formula for generating fatigue damage is:

[0037]

[0038] Among them, Hp is fatigue damage and Hu is stress damage.

[0039] Furthermore, the specific logic for generating the actual fatigue life is:

[0040] The maximum fatigue value of the jacket platform is calculated by correcting the fatigue life and the real-time stress value. The residual damage value is obtained by subtracting the fatigue damage from the maximum fatigue value. The actual fatigue life is obtained by dividing the residual damage value by the real-time stress. The specific formula for calculating the maximum fatigue value is:

[0041] Mo=TD*F1

[0042] Among them, Mo is the maximum fatigue capacity, TD is the corrected fatigue life, and F1 is the real-time stress;

[0043] The specific formula used to generate the actual fatigue life is:

[0044] Ms=Mo-Hp

[0045] Among them, Ms is the actual fatigue amount, and Hp is the fatigue damage;

[0046] The specific formula used to generate the actual fatigue life is:

[0047]

[0048] Where Tn is the actual fatigue life.

[0049] The present invention further provides a digital twin-based online prediction system for fatigue life of a jacket-type platform, the system is used to implement the digital twin-based online prediction method for fatigue life of a jacket-type platform, specifically comprising:

[0050] A data acquisition module is used to collect historical stress test data of jacket-type platform materials, material property data of jacket-type platform, stress data and environmental data; the historical stress test data includes test stress magnitude and test fatigue life; the jacket-type platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity;

[0051] A modeling optimization module is used to construct a data set with historical stress magnitudes, build an ideal fatigue life prediction model with the test fatigue life as a label, and use the data set to train and optimize the ideal fatigue life prediction model to obtain the ideal fatigue life prediction model after training;

[0052] A preliminary correction module is used to extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on environmental data, generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life;

[0053] The damage calculation module is used to perform damage analysis on stress data to calculate the cumulative stress damage, obtain the material fatigue resistance according to the material property data of the jacket platform, and generate fatigue damage according to the cumulative stress damage and material fatigue resistance; perform secondary correction on the corrected fatigue life through fatigue damage to obtain the actual fatigue life;

[0054] The digital twin module is used to build a digital twin platform, transmit the stress data and environmental data of the jacket-type platform to the jacket-type platform digital twin platform to build a digital model of the jacket-type platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket-type platform.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention generates an environmental correction factor through environmental data, and uses the correction factor to correct the predicted ideal fatigue life, fully considering the impact of environmental factors on fatigue life, so that the fatigue life prediction in the marine environment is more accurate. In addition, the present invention performs damage analysis on all previous stress data, calculates the cumulative stress damage that reflects the damage of the jacket-type platform materials, and based on this, performs a secondary correction on the predicted fatigue life to improve the reliability of the prediction results. Through the dual correction mechanism, the present invention can more comprehensively consider the impact of actual working conditions on the fatigue life of the jacket-type platform, thereby significantly improving the accuracy and reliability of fatigue life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0058] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0059] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0060] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0061] Example:

[0062] See also Figure 1 , the present invention provides a technical solution:

[0063] An online prediction method for fatigue life of a jacket platform based on digital twin, the specific steps include:

[0064] Step 1: Collect historical stress test data of jacket platform materials, material property data, stress data and environmental data of jacket platform; the historical stress test data includes test stress magnitude and test fatigue life; the jacket platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity;

[0065] The intersection of the diagonal brace is the stress concentration position of the conductor frame. The stress damage at this position directly determines the fatigue life of the entire conductor frame platform. The stress test data is obtained by performing fatigue life tests on the materials at the intersection of the diagonal braces of the conductor frame platform. The fatigue test is performed on the materials by a fatigue testing machine in the laboratory, and the number of cycles at different stress levels is measured until the material breaks. The SN curve is used to determine the fatigue limit of the material. The toughness of the material is measured by the Charpy impact test; the corrosion resistance of the coating is measured by the salt spray test. The specific logic is: collect salt spray data in the ocean, and use this configuration to simulate salt spray. The metal coating of the conductor frame platform material is placed in the configured simulated salt spray environment, and the time required for the metal coating to be completely corroded is recorded. The above recorded time is divided by the thickness of the metal coating to obtain the corrosion resistance of the coating. These material data can reflect the ability of the material at the intersection of the diagonal brace to resist stress damage and corrosion. The stress data and environmental data of the junction of the diagonal braces of the jacket-type platform are measured by stress sensors, temperature sensors, pH testers, dissolved oxygen sensors and salinity meters placed on the jacket-type platform; the stress data can provide an important basis for the estimation of stress damage, and the environmental data can provide an important basis for evaluating the corrosion capacity of the environment on the materials at the junction of the diagonal braces, and then for estimating the stress damage suffered by the materials at the junction of the diagonal braces.

[0066] Step 2: The historical stress magnitudes are used to form a data set, and an ideal fatigue life prediction model is constructed using the test fatigue life as a label. The ideal fatigue life prediction model is trained and optimized using the data set to obtain the ideal fatigue life prediction model after training.

[0067] A feedforward neural network is used, and the test fatigue life is used as a label. The ideal fatigue life prediction model is trained and optimized using a data set. It should be noted that the training and optimization of the ideal fatigue life prediction model using the test fatigue life as a label can adopt existing technologies, including: input layer, hidden layer, output layer and activation function, and the root mean square error loss function is used; the input data is calculated once through the network to obtain the output result, and the loss function is calculated according to the predicted value and the true value. The gradient of the loss function for each weight and bias is calculated by the chain rule, and the weight and bias of the network are updated using the gradient descent algorithm to minimize the loss function. Feedforward neural networks have strong nonlinear mapping capabilities. Fatigue life prediction usually involves complex material properties and multiple working conditions, and nonlinear relationships are difficult to describe using traditional linear models. Neural networks can capture complex nonlinear relationships through multiple hidden layers, thereby more accurately predicting fatigue life.

[0068] Step 3: Extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on temperature, seawater pH, dissolved oxygen content and salinity to generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life;

[0069] The specific logic for extracting strain and stress is: calculate the average stress value between each stress maximum and the adjacent minimum, and perform weighted mean operation on the average stress value to obtain the strain and stress; the specific formula for calculating the average stress value is:

[0070]

[0071] in, is the average stress value, T is the total time of the time series data, and F(t) is the stress time series data;

[0072] The specific logic for obtaining strain stress is:

[0073]

[0074] Where Ff is strain stress, t i is the time interval corresponding to the i-th average stress value, is the i average stress value, and n is the number of average stress values ​​in the stress time series data. The strain stress Ff comprehensively reflects the comprehensive situation of the stress data. The larger its value is, the greater the comprehensive stress on the jacket type platform is. Its generation can provide an important basis for predicting the life of the jacket type platform.

[0075] The specific logic for generating the corrected fatigue life is as follows: input strain stress into the optimized ideal fatigue life prediction model ideal fatigue life, perform mathematical analysis on temperature, seawater pH value, dissolved oxygen content and salinity, generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate the corrected fatigue life; the specific formula for generating the environmental correction factors is as follows:

[0076] A=W(PH-7) 2 tan -1 C O *C Y

[0077] Among them, A is the environmental correction factor, W is the temperature, PH is the pH value of seawater, C O is the dissolved oxygen content, C Yis salinity; the environmental correction factor A reflects the comprehensive impact of the marine environment on the fatigue life of the jacket platform. The larger its value, the greater the negative impact of the marine environment on the fatigue life of the jacket. The generation of this environmental factor can provide an important basis for the accurate assessment of fatigue life. Temperature W and dissolved oxygen C O The larger the value, the more serious the biocorrosion of the jacket platform by microorganisms in the marine environment; pH value and salinity C Y The larger the value, the more severe the chemical corrosion of the marine environment on the jacket platform.

[0078] The specific formula based on which the corrected fatigue life is generated is:

[0079]

[0080] Among them, TD is the corrected fatigue life, and TD is the ideal fatigue life. The ideal fatigue life Td reflects the fatigue life of the jacket-type platform material under an ideal environment. The larger its value, the longer the fatigue life of the jacket-type platform; the corrected fatigue life TD reflects the fatigue life of the jacket-type platform under an offshore environment. The larger its value, the longer the fatigue life of the jacket-type platform material. The generation of the corrected fatigue life TD can provide an important basis for accurately predicting the fatigue life of the jacket-type platform.

[0081] Step 4: Perform damage analysis on stress data to calculate cumulative stress damage, obtain material fatigue resistance based on material property data of jacket-type platform, generate fatigue damage based on cumulative stress damage and material fatigue resistance; perform secondary correction on corrected fatigue life through fatigue damage to obtain actual fatigue life;

[0082] The specific logic for generating stress damage is: threshold processing is performed on stress data through fatigue limit, stress data is transformed into effective stress data, and stress damage is generated on effective stress data; the specific logic for generating effective stress data is:

[0083]

[0084] Among them, F i ′ is the effective stress data, F i is the stress data, F O is the fatigue limit; when the stress does not reach the fatigue limit, the fatigue life of the material is infinite. By performing threshold processing on the stress data, the effective stress data that can directly affect the fatigue life can be obtained.

[0085] The specific formula for generating stress damage is:

[0086]

[0087] Where Hu is stress damage, F′ i(t) is the effective stress time series data, and L is the length of the time series data. The stress damage Hu reflects the damage to the jacket type platform caused by the stress since the jacket type platform was installed. The larger the value, the more damage the jacket type platform suffers from stress.

[0088] The specific logic for generating fatigue damage is: the material fatigue resistance is obtained according to the material property data of the jacket platform, and fatigue damage is generated according to the accumulated stress damage and the material fatigue resistance; the specific logic for generating material fatigue resistance is:

[0089] K=F O *R*e Hi

[0090] Among them, K is the material fatigue resistance, F O is the fatigue limit, R is the toughness, and Hi is the corrosion resistance of the coating. The material fatigue resistance K reflects the ability of the jacket-type platform to resist external stress and marine erosion. The larger its value, the stronger the ability of the jacket-type platform to resist external stress and marine erosion.

[0091] The specific formula for generating fatigue damage is:

[0092]

[0093] Among them, Hp is fatigue damage and Hu is stress damage. Fatigue damage Hp reflects the fatigue damage of the jacket-type platform. The larger its value is, the more fatigue damage the jacket-type platform suffers.

[0094] The maximum fatigue value of the jacket platform is calculated by correcting the fatigue life and the real-time stress value. The residual damage value is obtained by subtracting the fatigue damage from the maximum fatigue value. The actual fatigue life is obtained by dividing the residual damage value by the real-time stress. The specific formula for calculating the maximum fatigue value is:

[0095] Mo=TD*F1

[0096] Among them, Mo is the maximum fatigue value, TD is the corrected fatigue life, and F1 is the real-time stress. The maximum fatigue value Mo reflects the stress that the jacket-type platform can withstand. The larger its value is, the more stress the jacket-type platform can withstand.

[0097] The specific formula used to generate the actual fatigue life is:

[0098] Ms=Mo-Hp

[0099] Among them, Ms is the actual fatigue amount, and Hp is the fatigue damage; the actual fatigue amount Ms reflects the stress that the jacket-type platform can still withstand;

[0100] The specific formula used to generate the actual fatigue life is:

[0101]

[0102] Among them, Tn is the actual fatigue life. The actual fatigue life Tn reflects the durability and reliability of the jacket platform under actual working conditions. The larger the value, the higher the durability and reliability.

[0103] Step 5: Build a digital twin platform, transmit the stress data and environmental data of the jacket platform to the digital twin platform of the jacket platform to build a digital model of the jacket platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket platform.

[0104] See also Figure 2 The present invention further provides a digital twin-based online prediction system for fatigue life of a jacket-type platform, the system is used to implement the digital twin-based online prediction method for fatigue life of a jacket-type platform, specifically comprising:

[0105] A data acquisition module is used to collect historical stress test data of jacket-type platform materials, material property data of jacket-type platform, stress data and environmental data; the historical stress test data includes test stress magnitude and test fatigue life; the jacket-type platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity;

[0106] A modeling optimization module is used to construct a data set with historical stress magnitudes, build an ideal fatigue life prediction model with the test fatigue life as a label, and use the data set to train and optimize the ideal fatigue life prediction model to obtain the ideal fatigue life prediction model after training;

[0107] A preliminary correction module is used to extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on environmental data, generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life;

[0108] The damage calculation module is used to perform damage analysis on stress data to calculate the cumulative stress damage, obtain the material fatigue resistance according to the material property data of the jacket platform, and generate fatigue damage according to the cumulative stress damage and material fatigue resistance; perform secondary correction on the corrected fatigue life through fatigue damage to obtain the actual fatigue life;

[0109] The digital twin module is used to build a digital twin platform, transmit the stress data and environmental data of the jacket-type platform to the jacket-type platform digital twin platform to build a digital model of the jacket-type platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket-type platform.

[0110] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An online prediction method for fatigue life of a jacket platform based on digital twin, characterized in that: The specific steps include: Step 1: Collect historical stress test data of jacket platform materials, material property data, stress data and environmental data of jacket platform; the historical stress test data includes test stress magnitude and test fatigue life; the jacket platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity; Step 2: The historical stress magnitudes are used to form a data set, and an ideal fatigue life prediction model is constructed using the test fatigue life as a label. The ideal fatigue life prediction model is trained and optimized using the data set to obtain the ideal fatigue life prediction model after training. Step 3: Extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on environmental data to generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life; Step 4: Perform damage analysis on stress data to calculate cumulative stress damage, obtain material fatigue resistance based on material property data of jacket-type platform, generate fatigue damage based on cumulative stress damage and material fatigue resistance; perform secondary correction on corrected fatigue life through fatigue damage to obtain actual fatigue life; Step 5: Build a digital twin platform, transmit the stress data and environmental data of the jacket platform to the digital twin platform of the jacket platform to build a digital model of the jacket platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket platform.

2. According to claim 1, a method for online prediction of fatigue life of a jacket platform based on digital twin, characterized in that: The specific logic for extracting strain and stress is: Calculate the average stress value between each stress maximum and the adjacent minimum, and perform weighted mean operation on the average stress value to obtain the strain stress; the specific formula for calculating the average stress value is: in, is the average stress value, T is the total time of the time series data, and F(t) is the stress time series data; The specific logic for obtaining strain stress is: Where Ff is strain stress, t i is the time interval corresponding to the i-th average stress value, is the i average stress value, and n is the number of average stress values ​​in the stress time series data.

3. According to claim 1, a method for online prediction of fatigue life of a jacket platform based on digital twin, characterized in that: The specific logic for generating the corrected fatigue life is: Input strain stress into the optimized ideal fatigue life prediction model ideal fatigue life, perform mathematical analysis on environmental data, generate environmental correction factor, and use environmental correction factor to correct ideal fatigue life to generate corrected fatigue life; the specific formula for generating environmental correction factor is: A=W(PH-7) 2 tan -1 C O *C Y Among them, A is the environmental correction factor, W is the temperature, PH is the pH value of seawater, C o is the dissolved oxygen content, C Y is salinity; The specific formula based on which the corrected fatigue life is generated is: Among them, TD is the corrected fatigue life and Td is the ideal fatigue life.

4. According to claim 1, a method for online prediction of fatigue life of a jacket platform based on digital twin, characterized in that: The specific logic for generating stress damage is: The stress data is threshold processed through fatigue limit, the stress data is transformed into effective stress data, and stress damage is generated for the effective stress data; the specific logic for generating effective stress data is: Among them, F i ′ is the effective stress data, F i is stress data, F o is the fatigue limit; The specific formula for generating stress damage is: Where Hu is stress damage, F′ i (t) is the effective stress time series data, and L is the length of the time series data.

5. According to claim 1, a method for online prediction of fatigue life of a jacket platform based on digital twin, characterized in that: The specific logic for generating fatigue damage is: The material fatigue resistance is obtained based on the material property data of the jacket platform, and fatigue damage is generated based on the accumulated stress damage and the material fatigue resistance. The specific logic for generating the material fatigue resistance is: K=F O *R*e Hi Among them, K is the material fatigue resistance, F O is the fatigue limit, R is the toughness, and Hi is the corrosion resistance of the coating; The specific formula for generating fatigue damage is: Among them, Hp is fatigue damage and Hu is stress damage.

6. According to claim 1, a method for online prediction of fatigue life of a jacket platform based on digital twin, characterized in that: The specific logic for generating the actual fatigue life is: The maximum fatigue value of the jacket platform is calculated by correcting the fatigue life and the real-time stress value. The residual damage value is obtained by subtracting the fatigue damage from the maximum fatigue value. The actual fatigue life is obtained by dividing the residual damage value by the real-time stress. The specific formula for calculating the maximum fatigue value is: Mo=TD*F1 Among them, Mo is the maximum fatigue capacity, TD is the corrected fatigue life, and F1 is the real-time stress; The specific formula used to generate the actual fatigue life is: Ms=Mo-Hp Among them, Ms is the actual fatigue amount, and Hp is the fatigue damage; The specific formula used to generate the actual fatigue life is: Where Tn is the actual fatigue life.

7. An online fatigue life prediction system for a jacket platform based on digital twin, characterized by: The system is used to implement the online prediction method for fatigue life of a jacket-type platform based on digital twins as described in any one of claims 1 to 6, and specifically includes: A data acquisition module is used to collect historical stress test data of jacket-type platform materials, material property data of jacket-type platform, stress data and environmental data; the historical stress test data includes test stress magnitude and test fatigue life; the jacket-type platform material property data includes fatigue limit, toughness and coating corrosion resistance; the stress data includes stress magnitude time series data, and the environmental data includes the ambient temperature of the sea area where the platform is located, seawater pH value, dissolved oxygen content and salinity; A modeling optimization module is used to construct a data set with historical stress magnitudes, build an ideal fatigue life prediction model with the test fatigue life as a label, and use the data set to train and optimize the ideal fatigue life prediction model to obtain the ideal fatigue life prediction model after training; A preliminary correction module is used to extract features from stress data to obtain strain stress, input strain stress into the optimized ideal fatigue life prediction model to obtain ideal fatigue life, perform mathematical analysis on environmental data, generate environmental correction factors, and use the environmental correction factors to correct the ideal fatigue life to generate corrected fatigue life; The damage calculation module is used to: perform damage analysis on stress data to calculate the cumulative stress damage, obtain material fatigue resistance based on the material property data of the jacket platform, generate fatigue damage based on the cumulative stress damage and material fatigue resistance; perform secondary correction on the corrected fatigue life through fatigue damage to obtain the actual fatigue life; The digital twin module is used to build a digital twin platform, transmit the stress data and environmental data of the jacket-type platform to the jacket-type platform digital twin platform to build a digital model of the jacket-type platform, and realize high-precision real-time mapping between the physical model and the digital model of the jacket-type platform.

Images