A method and apparatus for fatigue damage assessment of a floating platform

Abstract

The application discloses a kind of floating platform fatigue damage evaluation method and device, to solve the technical problem that the fatigue damage of the existing floating platform fatigue damage evaluation method is difficult to realize comprehensive evaluation of floating platform fatigue damage by arranging a limited number of sensors.Method includes establishing floating platform finite element model and obtaining wave scatter diagram, by discrete long-term sea state determine the corresponding short-term working condition of each local structure;Subsequently, combined with preset regular wave, loading condition and other data, hot spot analysis method is used to identify each fatigue hot spot;Then using time domain finite element and machine learning constructs hot spot stress prediction model;Finally, based on rainflow counting method and stress-life curve, the fatigue damage result of each fatigue hot spot is generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ocean engineering, and in particular to a floating platform fatigue damage assessment method and device. BACKGROUND

[0002] The floating platform is a large structure used for ocean development and operation, and is widely used in the fields of offshore oil and gas exploitation, wind power generation, ocean scientific research, etc. It has many advantages such as strong adaptability, high cost-effectiveness, high safety, and mature technology. However, the floating platform often produces reciprocating motion under the coupling action of wind, wave and current, and its structure is subjected to complex alternating loads, thereby causing structural fatigue damage and affecting the safety of the structure and the safety of personnel.

[0003] The floating platform usually operates in waters far from the coast, and is subjected to complex environmental loads and the continuous action of wind, wave and current. Its structure is subjected to alternating loads for a long time, and is therefore prone to fatigue fracture. Therefore, it is very important to analyze and assess the fatigue damage of the floating platform structure in a timely manner through field monitoring, so as to obtain the safety condition of the platform structure in real time and provide an important basis for efficient production, safe operation and timely maintenance.

[0004] Most of the existing floating platform fatigue damage assessment methods monitor stress responses under different sea conditions by arranging a limited number of sensors, obtain hot spot stress data by linear extrapolation, and then perform fatigue analysis by using the rain flow counting method combined with S-N curves. However, the main dimension of the floating platform is large, and there are numerous fatigue hot spots. In addition, due to the high cost of arrangement and the limited physical space, some fatigue hot spots do not have the condition to directly monitor the stress, making it difficult to achieve comprehensive evaluation of the fatigue damage of the floating platform. SUMMARY

[0005] The present application provides a floating platform fatigue damage assessment method and device, which solves the technical problem that most of the existing floating platform fatigue damage assessment methods arrange a limited number of sensors, making it difficult to achieve comprehensive evaluation of the fatigue damage of the floating platform.

[0006] The present application provides a floating platform fatigue damage assessment method, which comprises:

[0007] obtaining a wave scatter diagram of a working sea area of a floating platform, and establishing a corresponding floating platform overall finite element model of the floating platform;

[0008] discretizing long-term sea conditions in the wave scatter diagram based on the wave scatter diagram and a plurality of preset wave spectra, and determining a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model;

[0009] determining a plurality of fatigue hot spots by performing fatigue hot spot analysis on the overall finite element model of the floating platform according to a plurality of pre-set regular wave sea states, the wave scatter diagram, a plurality of pre-set loading conditions of the floating platform, and a plurality of short-term sea states corresponding to each local structure, by using a pre-set fatigue hot spot analysis method;

[0010] constructing a fatigue hot spot stress response prediction model according to each fatigue hot spot, each pre-set loading condition of the floating platform, each pre-set wave spectrum, and a plurality of stress monitoring points of the floating platform, by using a time-domain finite element method and a machine learning algorithm;

[0011] generating fatigue damage results of each fatigue hot spot according to each stress monitoring point, an extreme environmental load condition corresponding to the floating platform, a plurality of pre-set loading conditions of the floating platform, a plurality of short-term sea states corresponding to each local structure, and a pre-set stress-life curve, by using the fatigue hot spot stress response prediction model based on a three-point rainflow counting method and the time-domain finite element method.

[0012] Optionally, the pre-set fatigue hot spot analysis method includes offshore mobile platform classification rules, stress response under dangerous working conditions, and a fatigue spectrum analysis method; and the determining a plurality of fatigue hot spots by performing fatigue hot spot analysis on the overall finite element model of the floating platform according to a plurality of pre-set regular wave sea states, the wave scatter diagram, a plurality of pre-set loading conditions of the floating platform, and a plurality of short-term sea states corresponding to each local structure, by using a pre-set fatigue hot spot analysis method, includes:

[0013] performing analysis on the overall finite element model of the floating platform based on the offshore mobile platform classification rules to determine a plurality of fatigue hot spots;

[0014] performing analysis on the overall finite element model of the floating platform based on the stress response under dangerous working conditions to determine a plurality of fatigue hot spots;

[0015] performing analysis on the overall finite element model of the floating platform according to a plurality of pre-set regular wave sea states, the wave scatter diagram, a plurality of pre-set loading conditions of the floating platform, and a plurality of short-term sea states corresponding to each local structure, by using the fatigue spectrum analysis method, to determine a plurality of fatigue hot spots.

[0016] Optionally, the performing analysis on the overall finite element model of the floating platform according to a plurality of pre-set regular wave sea states, the wave scatter diagram, a plurality of pre-set loading conditions of the floating platform, and a plurality of short-term sea states corresponding to each local structure, by using the fatigue spectrum analysis method, to determine a plurality of fatigue hot spots, includes:

[0017] performing stress transfer function construction on each local structure of the overall finite element model of the floating platform under each pre-set regular wave sea state and each pre-set loading condition of the floating platform to generate a plurality of stress transfer functions corresponding to each local structure.

[0018] determining wave spectra of each of the local structures under each of the short-term sea states based on the plurality of short-term sea states corresponding to each of the local structures;

[0019] calculating stress energy spectral densities of each of the local structures under each of the short-term sea states according to the plurality of stress transfer functions corresponding to each of the local structures and the wave spectra of each of the local structures under each of the short-term sea states;

[0020] determining joint probabilities of significant wave heights and above-zero-crossing periods of each of the short-term sea states based on the wave scatter diagrams;

[0021] calculating total fatigue lives of each of the local structures according to the stress energy spectral densities of each of the local structures under each of the short-term sea states, and the joint probabilities of significant wave heights and above-zero-crossing periods of each of the short-term sea states;

[0022] sorting the total fatigue lives of each of the local structures in ascending order, and selecting local structures corresponding to the top pre-set number of total fatigue lives as fatigue hotspots.

[0023] Optionally, the fatigue hotspot stress response prediction model is constructed by using the time-domain finite element method and the machine learning algorithm according to each of the fatigue hotspots, each of the pre-set floating platform loading conditions, each of the pre-set wave spectra, and a plurality of stress monitoring points of the floating platform, and includes:

[0024] simulated stress response time history data of the plurality of stress monitoring points and simulated stress response time history data of the plurality of fatigue hotspots are output by using the time-domain finite element method according to each of the pre-set floating platform loading conditions, wave characteristic parameters corresponding to each of the pre-set wave spectra, the plurality of stress monitoring points, and positions of the plurality of fatigue hotspots;

[0025] a fatigue hotspot stress response prediction model is constructed based on the machine learning algorithm, with the simulated stress response time history data of the plurality of stress monitoring points as input and the simulated stress response time history data of the plurality of fatigue hotspots as output.

[0026] Optionally, the fatigue damage results include fatigue damage per year and remaining fatigue life; and the fatigue damage results of each of the fatigue hotspots are generated by using the fatigue hotspot stress response prediction model according to each of the stress monitoring points, extreme environmental load conditions corresponding to the floating platform, the plurality of pre-set floating platform loading conditions, the plurality of short-term sea states corresponding to each of the local structures, and pre-set stress-life curves based on the three-point rainflow counting method and the time-domain finite element method.

[0027] Based on the three-point rainflow counting method, the fatigue hot spot stress response prediction model is used to calculate the fatigue damage of each fatigue hot spot within the monitoring time according to the monitoring stress response time history data corresponding to each stress monitoring point and the preset stress-life curve.

[0028] The three-point rainflow counting method and the time-domain finite element method are used to calculate the fatigue damage of each fatigue hot spot caused by long-term environmental load according to the preset stress-life curve, a plurality of preset floating platform loading conditions, and a plurality of short-term sea states corresponding to each local structure.

[0029] The three-point rainflow counting method and the time-domain finite element method are used to calculate the fatigue damage of each fatigue hot spot under extreme conditions according to the extreme environmental load conditions corresponding to the floating platform, a plurality of preset floating platform loading conditions, and the preset stress-life curve.

[0030] The monitoring time fatigue damage, the long-term environmental load caused fatigue damage, and the extreme condition fatigue damage of each fatigue hot spot are added respectively to determine the cumulative fatigue damage of each fatigue hot spot.

[0031] Based on the cumulative fatigue damage of each fatigue hot spot, the annual fatigue damage and the remaining fatigue life of each fatigue hot spot are calculated.

[0032] Optionally, based on the three-point rainflow counting method, the fatigue hot spot stress response prediction model is used to calculate the fatigue damage of each fatigue hot spot within the monitoring time according to the monitoring stress response time history data corresponding to each stress monitoring point and the preset stress-life curve, comprising:

[0033] The monitoring stress response time history data corresponding to each stress monitoring point is taken as the input of the fatigue hot spot stress response prediction model, and the first stress response time history data of a plurality of fatigue hot spots is output.

[0034] The three-point rainflow counting method is used to analyze the first stress time history data of a plurality of fatigue hot spots to determine a plurality of first stress cycle amplitudes and stress range cycle times corresponding to each first stress cycle amplitude.

[0035] According to the preset stress-life curve and a plurality of first stress cycle amplitudes, the average number of times of fatigue failure of the structure corresponding to each first stress cycle amplitude is determined.

[0036] According to the average number of times of fatigue failure of the structure corresponding to each first stress cycle amplitude and the stress range cycle times, the fatigue damage of each fatigue hot spot within the monitoring time is calculated.

[0037] Optionally, the step of using the three-point rainflow counting method and the time-domain finite element method to calculate the fatigue damage caused by the long-term environmental load of each fatigue hotspot based on the pre-set stress-life curve, multiple pre-set floating platform loading conditions, and multiple short-term sea states corresponding to each local structure includes:

[0038] The second stress time history data of multiple fatigue hot spots are determined using the time-domain finite element method based on multiple short-term sea states and multiple pre-set floating platform loading conditions corresponding to each local structure.

[0039] The three-point rainflow counting method is used to analyze the second stress time history data of multiple fatigue hot spots to determine multiple second stress cycle amplitudes and the number of stress range cycles corresponding to each second stress cycle amplitude;

[0040] Based on the preset stress-life curve and multiple second stress cycle amplitudes, determine the number of stress cycles required for the structure to undergo fatigue failure corresponding to each second stress cycle amplitude;

[0041] Based on the number of stress cycles and the number of stress range cycles required for the structure to undergo fatigue failure corresponding to each of the second stress cycle amplitudes, the fatigue damage caused by the long-term environmental load of each fatigue hot spot is calculated.

[0042] Optionally, the step of using the three-point rainflow counting method and the time-domain finite element method to calculate the fatigue damage under extreme conditions for each fatigue hotspot based on the extreme environmental load conditions corresponding to the floating platform, multiple pre-set floating platform loading conditions, and the pre-set stress-life curve includes:

[0043] The time-domain finite element method is used to determine the third stress time history data of multiple fatigue hot spots based on the extreme environmental load conditions corresponding to the floating platform and multiple pre-set floating platform loading conditions;

[0044] The three-point rainflow counting method is used to analyze the third stress time history data of multiple fatigue hot spots to determine multiple third stress cycle amplitudes and the number of stress range cycles corresponding to each third stress cycle amplitude.

[0045] Based on the preset stress-life curve and the multiple third stress cycle amplitudes, determine the number of stress cycles required for the structure to undergo fatigue failure corresponding to each third stress cycle amplitude;

[0046] Based on the number of stress cycles and the number of stress range cycles required for the structure to undergo fatigue failure corresponding to each of the third stress cycle amplitudes, calculate the fatigue damage under extreme working conditions for each of the fatigue hot spots.

[0047] The second aspect of the present application provides a floating platform fatigue damage evaluation device, comprising:

[0048] An acquisition module is configured to acquire a wave scatter diagram of a working sea area of a floating platform and establish a corresponding floating platform overall finite element model of the floating platform.

[0049] A determination module is configured to disperse long-term sea conditions in the wave scatter diagram based on the wave scatter diagram and a plurality of preset wave spectra, and determine a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model.

[0050] An analysis module is configured to perform fatigue hot spot analysis on the floating platform overall finite element model according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset floating platform loading conditions and a plurality of short-term sea conditions corresponding to each local structure by using a preset fatigue hot spot analysis method, and determine a plurality of fatigue hot spots.

[0051] A construction module is configured to construct a fatigue hot spot stress response prediction model according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum and a plurality of stress monitoring points of the floating platform by using a time-domain finite element method and a machine learning algorithm.

[0052] An evaluation module is configured to generate fatigue damage results of each fatigue hot spot according to each stress monitoring point, a corresponding extreme environmental load condition of the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea conditions corresponding to each local structure, a preset stress-life curve by using the fatigue hot spot stress response prediction model based on a three-point rain flow counting method and the time-domain finite element method.

[0053] The third aspect of the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the floating platform fatigue damage evaluation method according to any one of the above aspects.

[0054] From the above technical solutions, the present application has the following advantages:

[0055] The technical scheme of the present application provides a floating platform fatigue damage evaluation method, first, the wave scatter diagram of the working sea area of the floating platform is obtained, and the corresponding floating platform overall finite element model of the floating platform is established; then, based on the wave scatter diagram and a plurality of preset wave spectra, the long-term sea conditions in the wave scatter diagram are discretized, and a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model are determined; a plurality of fatigue hot spots are determined by performing fatigue hot spot analysis on the floating platform overall finite element model according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset floating platform loading conditions and a plurality of short-term sea conditions corresponding to each local structure, using a preset fatigue hot spot analysis method; a fatigue hot spot stress response prediction model is constructed according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum and a plurality of stress monitoring points of the floating platform, using a time domain finite element method and a machine learning algorithm; finally, based on the three-point rain flow counting method and the time domain finite element method, the fatigue hot spot stress response prediction model is used to generate fatigue damage results of each fatigue hot spot according to each stress monitoring point, the corresponding extreme environmental load condition of the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea conditions corresponding to each local structure, and a preset stress-life curve; based on the above scheme, the fatigue hot spot stress response prediction model is established using the machine learning algorithm, and the fatigue damage results of each fatigue hot spot in the floating platform are generated by combining the three-point rain flow counting method, the preset stress-life curve, thereby realizing comprehensive evaluation of the fatigue damage of the floating platform. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0057] Figure 1 A step flow chart of a floating platform fatigue damage evaluation method provided for the first embodiment of the present application;

[0058] Figure 2 A schematic diagram of floating platform meshing provided for the first embodiment of the present application;

[0059] Figure 3 A schematic diagram of fatigue hot spot and stress monitoring point distribution provided for the first embodiment of the present application;

[0060] Figure 4 A schematic diagram of fatigue hot spot and stress monitoring point distribution provided for the first embodiment of the present application;

[0061] Figure 5 A schematic diagram of a machine learning framework provided for the first embodiment of the present application;

[0062] Figure 6 A schematic diagram of fatigue hot spot stress response prediction data provided for the first embodiment of the present application;

[0063] Figure 7 A schematic diagram of fatigue hot spot stress prediction error analysis provided for the first embodiment of the present application;

[0064] Figure 8 A schematic diagram of a training loss curve provided for the first embodiment of the present application;

[0065] Figure 9 A schematic diagram of fatigue hot spot stress prediction value Vs real value provided for the first embodiment of the present application;

[0066] Figure 10 A flowchart of a floating platform fatigue damage assessment method provided for the first embodiment of the present application;

[0067] Figure 11 A structural block diagram of a floating platform fatigue damage assessment device provided for the second embodiment of the present application. DETAILED DESCRIPTION

[0068] The embodiments of the present application provide a floating platform fatigue damage assessment method and device, which are used to solve the technical problem that the existing floating platform fatigue damage assessment method is difficult to achieve comprehensive evaluation of floating platform fatigue damage by arranging a limited number of sensors.

[0069] In order to make the technical features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the following described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0070] Please refer to Figure 1 , Figure 1 A step flowchart of a floating platform fatigue damage assessment method provided for the first embodiment of the present application.

[0071] The floating platform fatigue damage assessment method provided by the present application comprises:

[0072] Step 101, obtaining a wave scatter diagram of a working sea area of a floating platform, and establishing a corresponding floating platform overall finite element model of the floating platform.

[0073] It should be noted that the established overall finite element model of the floating platform includes a wet surface model, a structure model, a mass model and a Morison model; the wet surface model is used to describe the surface of the floating platform in contact with the water body, and is mainly used to calculate the hydrodynamic load when the wave and the structure interact. The structure model is used to analyze the displacement, stress and strain of the floating platform, which is the key to evaluating the structural integrity and safety of the platform. The mass model is used to simulate the mass distribution of the floating platform, and the Morison model is used to calculate the wave force of slender structures (such as pontoons, columns, crossbars, etc.).

[0074] Exemplarily, assuming that the floating platform is 91.6m long, 76.0m wide, and the total weight is 26039t, as shown in Figure 2 The wet surface model, crossbar Morison model, structure model and mass model of the floating platform are established, and the finite element grid size is divided into 1m, a total of 32404 units, 28919 nodes, and the grid division is as shown in Figure 2 The main dimensions of the floating platform are shown in Table 1:

[0075] Table 1 Main dimensions of the floating platform

[0076]

[0077] Step 102, based on the wave scatter diagram and a plurality of preset wave spectra, the long-term sea state in the wave scatter diagram is discretized to determine a plurality of short-term sea states corresponding to each local structure in the overall finite element model of the floating platform.

[0078] The wave scatter diagram is the wave scatter diagram of the working sea area of the floating platform.

[0079] It should be noted that according to the wave scatter diagram of the working sea area of the floating platform, the selected wave spectrum (i.e. the preset wave spectrum), such as JONSWAP spectrum, Pierson-Moskowitz spectrum, Bretschneider spectrum, etc., the long-term sea state in the wave scatter diagram is discretized into a series of short-term sea states (i.e. a plurality of short-term sea states corresponding to each local structure in the overall finite element model of the floating platform).

[0080] Step 103, using the preset fatigue hot spot analysis method, a plurality of preset regular wave sea states, a wave scatter diagram, a plurality of preset floating platform loading conditions and a plurality of short-term sea states corresponding to each local structure are used to analyze the fatigue hot spot of the overall finite element model of the floating platform to determine a plurality of fatigue hot spots.

[0081] The preset fatigue hot spot analysis method includes the Offshore Mobile Platform Classification Code, stress response under dangerous working conditions and fatigue spectrum analysis method.

[0082] It should be noted that the fatigue hot spot refers to the area in the structure where fatigue cracks are prone to initiate and propagate due to factors such as geometric discontinuity, stress concentration, or material properties. These areas usually have a higher stress level and are high-risk locations for structural fatigue failure. For the floating platform to be evaluated, the fatigue hot spots are determined based on the offshore mobile platform classification rules, stress response under dangerous working conditions, and fatigue spectrum analysis method.

[0083] Specifically, step 103 can include the following sub-steps S31-S33:

[0084] Step S31, based on the offshore mobile platform classification rules, analyze the overall finite element model of the floating platform to determine a plurality of fatigue hot spots;

[0085] The offshore mobile platform classification rules are a set of technical standards and rules system for offshore mobile platforms (such as floating platforms, etc.). The core purpose is to ensure the safety, reliability, and structural integrity of offshore mobile platforms.

[0086] It should be noted that according to the offshore mobile platform classification rules, any weld that may produce potential fatigue cracks and structural forms that cause stress concentration should be designed for fatigue resistance. If necessary, fatigue analysis of the node details should be performed. The surface type platform, i.e. the floating platform, at least includes the following contents: the connection between the longitudinal bone and the transverse strong frame and the transverse bulkhead; the connection between the transverse strong frame and the outer plate, the bottom plate, the inner bottom plate, and the bulkhead plate; the connection between the bottom edge cabin inclined plate and the inner bottom plate and the longitudinal bulkhead plate; the connection between the longitudinal / transverse girder end elbow plate. Therefore, these parts are determined as fatigue hot spots.

[0087] Step S32, based on the stress response under dangerous working conditions, analyze the overall finite element model of the floating platform to determine a plurality of fatigue hot spots;

[0088] Stress response under dangerous working conditions: In structures such as floating platforms, dangerous working conditions refer to special and potentially threatening working states of the structure, such as the floating platform being under maximum lateral stress, maximum torsional stress, maximum longitudinal shear, maximum vertical bending, etc. Stress response refers to the stress condition of the structure under these dangerous working conditions. Fatigue hot spots are usually areas of fatigue stress concentration, and the stress response under dangerous working conditions can reflect whether the structure is prone to fatigue failure.

[0089] It should be noted that fatigue hot spots are usually areas of fatigue stress concentration, so the stress response under dangerous working conditions can reflect whether the structure is prone to fatigue failure. Stress concentration refers to the phenomenon that the local stress is significantly higher than the average stress in the structure due to geometric discontinuity or uneven material properties, which can be measured by the stress concentration factor. wherein is the stress concentration factor, the maximum stress, the average stress.

[0090] Further, according to the DNV (Det Norske Veritas) recommendations, the maximum stress and stress concentration area of the platform under the maximum transverse stress state, the maximum torsion stress state, the maximum longitudinal shear state and the maximum vertical bending state are checked, and the part is determined as the fatigue hot spot.

[0091] Further, the maximum transverse stress state is that the floating platform is subjected to 90-degree wave direction, and the wavelength is twice the distance between the outer edges of the two pontoons. In this state, the cross brace is subjected to a large transverse separation force and transverse extrusion force. The maximum torsion stress state is that the floating platform is subjected to 45-degree wave direction, and the wavelength is the diagonal length. In this state, the structure is not only subjected to torque but also separation force. The maximum longitudinal shear state is that the floating platform is subjected to 45-degree wave direction, and the wavelength is 1.5 times the diagonal length. When the phase is 180 degrees, the longitudinal shear force can cause high shear stress in the connection nodes, the connection between the column and the pontoon, and other parts of the platform. These areas are often fatigue hot spots. The maximum vertical bending state is that the floating platform is subjected to 0-degree wave direction, and the wavelength is the length of the pontoon. When the wave phase is 0 degrees, the middle part of the platform is at the wave crest, and the bow and stern parts are at the wave trough. At this time, the buoyancy of the middle part is greater than the gravity, and the buoyancy of the bow and stern parts is less than the gravity. The structure occurs hogging phenomenon. When the wave phase is 180 degrees, similarly, the structure occurs sagging phenomenon.

[0092] Therefore, the above four regular wave working conditions are loaded to the floating platform to obtain the stress response of the floating platform under the dangerous working condition. The maximum stress and stress concentration part under each working condition are determined as the fatigue hot spot.

[0093] Exemplarily, please refer to Figures 3-4 The fatigue hot spot and stress monitoring point distribution are shown in Figures 3-4 The fatigue damage degree of the fatigue hot spot and stress monitoring point is shown in Table 2:

[0094] Table 2 Fatigue damage degree of fatigue hot spot and stress monitoring point

[0095]

[0096] Step S33, a fatigue spectrum analysis method is adopted to analyze the overall finite element model of the floating platform according to a plurality of preset regular wave sea conditions, a wave scatter diagram, a plurality of preset floating platform loading working conditions and a plurality of short-term sea conditions corresponding to each local structure, to determine a plurality of fatigue hot spots.

[0097] Fatigue spectrum analysis method is a fatigue life evaluation method based on frequency domain, which has small amount of calculation and high precision, and can basically meet the engineering requirements, especially suitable for fatigue analysis of structures under complex working conditions and random loads.

[0098] Specifically, step S33 can include the following sub-steps S331-S336:

[0099] Step S331, stress transfer function construction is performed on each local structure of the overall finite element model of the floating platform under each preset regular wave sea state and each preset floating platform loading condition, to generate a plurality of stress transfer functions corresponding to each local structure;

[0100] It should be noted that a series of regular wave sea states (i.e. a plurality of preset regular wave sea states), a plurality of preset floating platform loading conditions, determine the stress transfer functions of each local structure of the overall finite element model of the floating platform under a series of regular wave sea states under different loading conditions (preset floating platform loading conditions), i.e. a plurality of stress transfer functions corresponding to each local structure . Among them is the wave direction angle, is the wave frequency.

[0101] Step S332, based on the plurality of short-term sea states corresponding to each local structure, determine the wave spectrum of each local structure under each short-term sea state;

[0102] It should be noted that according to the wave scatter diagram of the working sea area of the floating platform, the selected wave spectrum, such as JONSWAP spectrum, Pierson-Moskowitz spectrum, Bretschneider spectrum, etc., after the long-term sea state is dispersed into a series of short-term sea states, the wave spectrum of each local structure under each short-term sea state is obtained , wherein is the significant wave height, is the zero-crossing period.

[0103] Step S333, according to the plurality of stress transfer functions corresponding to each local structure and the wave spectrum of each local structure under each short-term sea state, calculate the stress energy spectrum density of each local structure under each short-term sea state;

[0104] It should be noted that according to the stress transfer function , the wave spectrum , the stress energy spectrum density of each local structure under each short-term sea state , the calculation formula of the stress energy spectrum density is:

[0105] ;

[0106] Step S334, based on the wave scatter diagram, determine the joint probability of the significant wave height and the above zero-crossing period of each short-term sea state;

[0107] It should be noted that the wave scatter diagram is discretized into a series of short-term sea states according to the selected wave spectrum, and the results of the short-term sea state are the significant wave height, the above zero-crossing period, and the probability of the two, i.e., the joint probability of the significant wave height and the above zero-crossing period of each short-term sea state p i .

[0108] Step S335, according to the stress energy spectrum density of each local structure under each short-term sea state, the joint probability of the significant wave height and the above zero-crossing period of each short-term sea state, calculate the total fatigue life of each local structure;

[0109] It should be noted that the probability density function of the short-term distribution of the stress range is assumed to conform to the Rayleigh distribution. By applying the obtained spectrum moment, the average above zero-crossing period f and the spectrum width parameter of the probability density function of the short-term distribution of the stress range can be calculated according to the following formula:

[0110] The probability density function of the Rayleigh distribution :

[0111] ;

[0112] The average above zero-crossing period:

[0113] ;

[0114] The spectrum width parameter:

[0115] ;

[0116] wherein S is the stress range (twice the stress amplitude), , , , are the zero-order moment, the second-order moment, and the fourth-order moment of the stress spectrum, respectively.

[0117] Specifically, first, the spectrum moment of the stress energy spectrum is calculated by using the stress energy spectrum density, and the calculation process is specifically as follows:

[0118] ;

[0119] wherein is the spectrum moment of the nth-order stress energy spectrum; is the nth power of the frequency , and n takes the corresponding value (2 / 0).

[0120] Then, the above zero-crossing frequency of the stress response is calculated by using the spectrum moment of the stress energy spectrum, and the Rayleigh distribution probability density wherein, is the upper zero-crossing frequency of the stress response of the local structure under the i-th short-term sea state; is the spectral moment of the 2nd order stress energy spectrum of the local structure under the i-th short-term sea state, i.e. the 2nd order moment of the stress spectrum of the local structure under the i-th short-term sea state; is the spectral moment of the 0th order stress energy spectrum of the local structure under the i-th short-term sea state, i.e. the 0th order moment of the stress spectrum of the local structure under the i-th short-term sea state; is the Rayleigh distribution probability density of the local structure under the i-th short-term sea state; is the standard deviation of the stress of the local structure under the i-th short-term sea state, used to represent the dispersion degree or the width of the stress range distribution. It reflects the fluctuation of the stress amplitude, and a larger indicates that the difference of the stress amplitude is larger, and a smaller indicates that the stress amplitude is relatively concentrated, ; is the stress range (twice the stress amplitude).

[0121] Further, the short-term fatigue damage caused by each local structure under each short-term sea state is calculated by using the joint probability of the upper zero-crossing frequency of the stress response, the Rayleigh distribution probability density, the significant wave height and the upper zero-crossing period, and the short-term fatigue damage caused by each local structure under each short-term sea state is accumulated respectively, so as to obtain the cumulative damage of each local structure; specifically, the cumulative fatigue damage is calculated by applying the Palmgren-Miner linear cumulative damage theory, when the probability density function of the short-term distribution of the stress range generated by a short-term sea state can be represented by the Rayleigh distribution, the form of the S-N curve is assumed to be N=KS -m , then the short-term fatigue damage caused by the i-th short-term sea state, i.e. the short-term fatigue damage caused by the local structure under the i-th short-term sea state, is:

[0122] ;

[0123] wherein, is the short-term fatigue damage caused by the local structure under the i-th short-term sea state; T is the design life; K and m are two physical parameters defining the S-N curve; is the upper zero-crossing frequency of the stress response of the local structure under the i-th short-term sea state, i.e. the average action frequency of the stress range, with the unit of hertz; is the joint probability of the significant wave height and the upper zero-crossing period of the i-th short-term sea state; is the Rayleigh distribution probability density of the local structure under the i-th short-term sea state, indicating the probability density of the local structure generating the S value under the i-th short-term sea state; S is the stress range, In a short-term sea state, there are many stress amplitude values, and the numerical values are different, so there are m amplitude values, and the probability of each is 1 / m, but many stress amplitude values are similar, so similar stress amplitude values are combined, and finally the number of stress amplitude values is greatly reduced, such as stress amplitude values of 【10, 11】MPa are considered as 10.5MPa, and the m stress amplitude values are calculated respectively by default.

[0124] Further, the damage caused by M short-term sea states in the wave scatter diagram is accumulated to obtain the total cumulative damage D, that is, the cumulative damage of each local structure, and the calculation process can be represented as:

[0125] ;

[0126] Wherein, D is the cumulative damage of the local structure; is the "average" frequency of the stress range S of the calculation point in the entire life cycle of the structure, with the unit of hertz, ; M is the total number of short-term sea states.

[0127] Finally, the total fatigue life of each local structure is calculated by using the cumulative damage of each local structure, wherein the total fatigue life The calculation process is as follows:

[0128] ;

[0129] It is worth mentioning that the present application introduces the probability density function of stress range distribution and the total cycle number N of the structure design life T , and can obtain:

[0130] ;

[0131] Based on the above basis, the total cumulative fatigue damage D can also be written as:

[0132] ;

[0133] Wherein, is the mth power of the stress range S; m is a physical parameter in the S-N curve.

[0134] Step S336, sort the total fatigue life of each local structure in ascending order, and select the local structure corresponding to the total fatigue life of the first preset number of positions as the fatigue hot spot.

[0135] It should be noted that based on the above steps, for the established overall finite element model of the floating platform, the total fatigue life of each local part of the floating platform is obtained by using the fatigue spectrum analysis method, the total fatigue life is sorted from short to long (small to large), a series of points in the front (such as the top 5%, which can be adjusted according to the complexity of the structure and the amount of calculation) with the shortest total fatigue life are selected, and the local structure corresponding to the total fatigue life of the front preset number of points is determined as the fatigue hot spot.

[0136] In summary, the fatigue hot spots determined based on the offshore platform classification specification, the dangerous working condition stress response and the fatigue spectrum analysis method are counted, and the union of the three is taken, and finally N fatigue hot spots are determined. In addition, according to the current stress monitoring device installation situation of the floating platform, M stress monitoring points are determined.

[0137] Step 104, using the time domain finite element method and the machine learning algorithm, a fatigue hot spot stress response prediction model is constructed according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum and multiple stress monitoring points of the floating platform.

[0138] Specifically, step 104 can include the following sub-steps S41-S42:

[0139] Step S41, using the time domain finite element method, according to the positions of the multiple stress monitoring points and the multiple fatigue hot spots, the simulation stress response time history data of the multiple stress monitoring points and the simulation stress response time history data of the multiple fatigue hot spots are outputted according to the wave characteristic parameters corresponding to each preset floating platform loading condition and each preset wave spectrum;

[0140] Step S42, based on the machine learning algorithm, a fatigue hot spot stress response prediction model is constructed, which takes the simulation stress response time history data of the multiple stress monitoring points as input and takes the simulation stress response time history data of the multiple fatigue hot spots as output.

[0141] It should be noted that the time domain finite element method is used to calculate the structural stress response under multiple combinations of input parameters, and the simulation stress response time history data of the multiple stress monitoring points and the simulation stress response time history data of the multiple fatigue hot spots are outputted, so as to establish a stress monitoring point and fatigue hot spot stress response time history database, and a prediction model (fatigue hot spot stress response prediction model) is constructed by using the machine learning algorithm, which takes the stress response of the monitoring point (simulation stress response time history data of the stress monitoring point) as input and takes the stress response of the fatigue hot spot (simulation stress response time history data of the fatigue hot spot) as output.

[0142] Further, in this step, according to the characteristics of the operation sea area, a series of platform loading conditions, wave directions , significant wave heights , spectral peak periods Input parameters including wave spectrum. The floating platform loading conditions include typical conditions such as self-propelled conditions, operation conditions, survival conditions, etc.; the wave spectrum includes typical wave spectrum types such as JONSWAP spectrum, Pierson-Moskowitz spectrum, Bretschneider spectrum, etc., and the corresponding wave spectrum is selected according to the operation sea area and the applicable range of the wave spectrum; significant wave height Starting from 1 m, with a step of 0.5 m, to the design survival limit state wave height; spectral peak period Starting from 2 s, with a step of 0.5 s, to 30 s; wave direction Starting from 0°, with a step of 5°, to 175°. Due to the symmetry of the floating platform, only the wave in the wave direction of [0, 180°] with a step of 5° needs to be simulated by the finite element method.

[0143] Further, the step is based on a machine learning method to construct a fatigue hot spot stress prediction model system. For the spatial coupling characteristics of the offshore platform structure, an adaptive neural network architecture driven by correlation analysis is used to determine the spatial configuration and scale of the input layer monitoring nodes through feature correlation analysis and data distribution evaluation. The model architecture is based on a multilayer perception mechanism to establish a nonlinear mapping relationship between the monitoring data and the target stress field, and the input layer is based on spatial correlation to quantify and select the time series stress data of the key monitoring points. In the model construction process, an adaptive gradient optimization algorithm is used to dynamically adjust the learning parameters, and a early stopping mechanism and regularization method are used to balance the model complexity and generalization ability. In addition, for each fatigue hot spot, a number of nearest monitoring points are selected as the input layer, and a dependency analysis is performed on the number of monitoring points to obtain the appropriate number of monitoring points under the target prediction accuracy. A multi-dimensional verification system is established in the performance evaluation stage to quantitatively evaluate the prediction accuracy, error stability and generalization performance from three aspects of prediction accuracy, error stability and generalization performance through three indicators of determination coefficient (R²), mean absolute error (MAE, Mean Absolute Error) and mean squared error (MSE, Mean Squared Error). The method realizes effective prediction of the stress field of complex marine structures through the collaborative optimization of data-driven and mechanism-constrained.

[0144] Exemplarily, a fatigue hot spot stress response prediction model based on a machine learning algorithm is constructed, which generates a fatigue hot spot stress response database from 6 stress monitoring points and fatigue hot spot stress time history data. The stress response data of the 6 stress monitoring points are used as the input layer, including two fully connected hidden layers, the first hidden layer is configured with 20 neurons, and the second hidden layer is configured with 10 neurons, and the machine learning framework is as shown in Figure 5 The stress response prediction data of the fatigue hot spot is as shown in Figure 6 Figures 6-7 ​The prediction error of the model on the validation set converges stably to within 8%, the mean absolute error (MAE) is 0.89 MPa, and the correlation coefficient (R²) is more than 0.91. Figure 8 The training loss curve shown verifies the effective convergence characteristics of the model, Figure 9 The prediction-actual comparison chart intuitively shows the high-precision prediction capability of the application in complex marine environments.

[0145] Step 105, based on the three-point rainflow counting method and the time-domain finite element method, using the fatigue hot spot stress response prediction model, according to the extreme environmental load conditions corresponding to each stress monitoring point and the floating platform, a plurality of preset floating platform loading working conditions, a plurality of short-term sea states corresponding to each local structure, and a preset stress-life curve, the fatigue damage results of each fatigue hot spot are generated.

[0146] The fatigue damage results include the fatigue damage occurring each year and the remaining fatigue life.

[0147] It should be noted that the cumulative fatigue damage of the fatigue hot spot is composed of the fatigue damage in the monitoring time, the fatigue damage caused by the long-term environmental load in the service period, and the damage caused by the extreme environmental load. The fatigue damage of the three parts is calculated respectively, the fatigue damage occurring each year of the fatigue hot spot is calculated, and finally the remaining fatigue life of the fatigue hot spot is obtained.

[0148] Specifically, step 105 can include the following sub-steps S51-S55:

[0149] Step S51, based on the three-point rainflow counting method, using the fatigue hot spot stress response prediction model, according to the monitoring stress response time history data corresponding to each stress monitoring point and the preset stress-life curve, the fatigue damage of each fatigue hot spot in the monitoring time is calculated;

[0150] Further, step S51 can include the following sub-steps S511-S514:

[0151] Step S511, taking the monitoring stress response time history data corresponding to each stress monitoring point as the input of the fatigue hot spot stress response prediction model, outputting the first stress response time history data of the plurality of fatigue hot spots;

[0152] Step S512, using the three-point rainflow counting method to analyze the first stress time history data of the plurality of fatigue hot spots, determining a plurality of first stress cycle amplitudes and stress range cycle times corresponding to each first stress cycle amplitude;

[0153] Step S513, according to the preset stress-life curve and the plurality of first stress cycle amplitudes, determining the average number of times of fatigue failure of the structure corresponding to each first stress cycle amplitude;

[0154] Step S514, according to the average number of fatigue damage of each first stress cycle amplitude corresponding structure and the stress range cycle number, the monitoring time of each fatigue hot spot fatigue damage is calculated.

[0155] It should be noted that the corresponding monitoring point stress time history data (i.e. the monitoring stress response time history data corresponding to each stress monitoring point) is input, and the stress time history of the N fatigue hot spots (i.e. the first stress response time history data of the plurality of fatigue hot spots) is obtained by using the constructed fatigue hot spot stress response prediction model. The rainflow counting method, the selected S-N curve (preset stress-life curve) is combined to calculate the fatigue damage of each fatigue hot spot in the stress monitoring time. Preferably, the stress prediction data of the stress monitoring point 3h is used for fatigue damage calculation, and the fatigue damage value is updated continuously.

[0156] Specifically, the three-point rainflow counting method is used to analyze the fatigue hot spot stress prediction data (first stress time history data of the fatigue hot spot), and for the kth fatigue hot spot, m groups of data of different stress cycle amplitudes (i.e. a plurality of first stress cycle amplitudes and stress range cycle numbers corresponding to each first stress cycle amplitude) are obtained, wherein k=1, 2, 3…, N. Based on the three-point rainflow counting method and the Miner-Palmgren damage accumulation theory, the fatigue damage of the kth fatigue hot spot in the monitoring time is:

[0157]

[0158] is the fatigue damage of the kth fatigue hot spot in the monitoring time; is the ith stress range cycle number after rainflow counting, i.e. the stress range cycle number corresponding to the ith first stress cycle amplitude; is the average number of fatigue damage of the structure under the action of the ith constant amplitude stress (first stress cycle amplitude) based on the S-N curve; m is the number of groups of different stress cycle amplitudes after rainflow counting, i.e. the total number of first stress cycle amplitudes.

[0159] Step S52, using the three-point rainflow counting method and the time domain finite element method, the fatigue damage of each fatigue hot spot caused by long-term environmental load is calculated according to the preset stress-life curve, a plurality of preset floating platform loading conditions, and a plurality of short-term sea states corresponding to each local structure.

[0160] Further, step S52 can include the following sub-steps S521-S524:

[0161] Step S521, using the time domain finite element method, the second stress time history data of the plurality of fatigue hot spots is determined according to the plurality of short-term sea states corresponding to each local structure and the plurality of preset floating platform loading conditions.

[0162] ​​Step S522, the second stress time history data of the plurality of fatigue hot spots are analyzed by using a three-point rain flow counting method to determine a plurality of second stress cycle amplitudes and stress range cycle numbers corresponding to each second stress cycle amplitude;

[0163] Step S523, according to the preset stress-life curve and the plurality of second stress cycle amplitudes, stress cycle numbers required for the structure to occur fatigue failure corresponding to each second stress cycle amplitude are determined.

[0164] Step S524, according to the stress cycle numbers required for the structure to occur fatigue failure corresponding to each second stress cycle amplitude and the stress range cycle numbers, fatigue damages of each fatigue hot spot caused by the long-term environmental load are calculated.

[0165] It should be noted that, in order to accurately predict the remaining fatigue life of the offshore platform, fatigue damage in the monitoring time should also be obtained. The fatigue damage in the service period is the fatigue damage generated before the platform is monitored, which is composed of fatigue damages caused by long-term and extreme environmental loads. Among them, the long-term environmental load refers to the statistical characteristics of the environmental conditions experienced by the offshore platform during the entire design life. This load reflects the comprehensive influence of various environmental factors that the platform may encounter during the entire service period.

[0166] Further, the fatigue damage of the kth fatigue hot spot caused by the long-term environmental load is calculated by using the frequency domain fatigue spectrum analysis method according to the wave scatter diagram of the service sea area of the floating platform and the S-N curve, k = 1, 2, 3…, N. Specifically, first, the time domain finite element calculation method is used to input the short-term sea conditions and the loading working conditions, i.e. a plurality of short-term sea conditions corresponding to each local structure and a plurality of preset floating platform loading working conditions, so as to obtain the fatigue hot spot stress response time history data (i.e. the second stress time history data of the plurality of fatigue hot spots), and then the three-point rain flow counting method is used to process the data to obtain a series of stress amplitudes and corresponding stress cycle numbers, i.e. a plurality of second stress cycle amplitudes and stress range cycle numbers corresponding to each second stress cycle amplitude, so as to calculate the fatigue damage of each fatigue hot spot caused by the long-term environmental load. The process is specifically as follows:

[0167] ;

[0168] Among them, is the fatigue damage of the kth fatigue hot spot caused by the long-term environmental load; is the service life before the stress monitoring of the floating platform; is the number of different stress amplitudes within one year under the action of the long-term environmental load, i.e. the total number of second stress cycle amplitudes; is the stress cycle number of the ith stress amplitude within one year under the action of the long-term environmental load, i.e. the stress range cycle number corresponding to the second stress cycle amplitude. the stress cycle number required for the structure to fail under the action of the i-th second stress cycle amplitude, i.e. the stress cycle number required for the structure to fail under the action of the i-th second stress cycle amplitude.

[0169] In step S53, the extreme working condition fatigue damage of each fatigue hot spot is calculated according to the extreme environmental load condition corresponding to the floating platform, the plurality of preset floating platform loading working conditions, and the preset stress-life curve, by using the three-point rainflow counting method and the time-domain finite element method.

[0170] The extreme environmental load refers to the most severe environmental condition that the offshore platform may encounter during its service period, such as a 50-year wave condition. The extreme environmental load has a short influence time but a large stress amplitude, and therefore the fatigue damage caused thereby cannot be ignored.

[0171] Specifically, step S53 can include the following sub-steps S531-S534:

[0172] In step S531, the third stress time history data of the plurality of fatigue hot spots is determined according to the extreme environmental load condition corresponding to the floating platform and the plurality of preset floating platform loading working conditions, by using the time-domain finite element method.

[0173] In step S532, the third stress cycle amplitude and the stress range cycle number corresponding to each third stress cycle amplitude are determined by analyzing the third stress time history data of the plurality of fatigue hot spots, by using the three-point rainflow counting method.

[0174] In step S533, the stress cycle number required for the structure to fail under the action of each third stress cycle amplitude is determined according to the preset stress-life curve and the plurality of third stress cycle amplitudes.

[0175] In step S534, the extreme working condition fatigue damage of each fatigue hot spot is calculated according to the stress cycle number required for the structure to fail under the action of each third stress cycle amplitude and the stress range cycle number.

[0176] It should be noted that the extreme load (extreme environmental load condition) encountered by the floating platform during its service period is counted, and the extreme environmental load condition and the platform loading working condition are input into a finite element calculation program. That is, the stress response of the floating platform under the extreme working condition (i.e. the third stress time history data of the plurality of fatigue hot spots) is obtained according to the extreme environmental load condition corresponding to the floating platform and the plurality of preset floating platform loading working conditions, by using the time-domain finite element method. The fatigue damage of the k-th fatigue hot spot under the extreme working condition (i.e. the extreme working condition fatigue damage of the fatigue hot spot) is calculated by using the three-point rainflow counting method and the Miner-Palmgren damage accumulation theory, k = 1, 2, 3, …, N.

[0177] ;

[0178] wherein, is the fatigue damage of the kth fatigue hot spot under the extreme working condition; is the number of cycles of the ith stress amplitude caused by the jth extreme working condition, i.e. the number of stress range cycles corresponding to the ith third stress cycle amplitude caused by the jth extreme working condition; is the number of stress cycles required for fatigue failure under the ith stress amplitude caused by the jth extreme working condition, i.e. the number of stress cycles required for fatigue failure of the structure under the ith third stress cycle amplitude caused by the jth extreme working condition; is the number of different stress amplitudes under extreme working conditions, i.e. the total number of third stress cycle amplitudes; m is the number of extreme working conditions encountered by the floating platform during the service period.

[0179] Step S54, the fatigue damage, the fatigue damage caused by long-term environmental load, and the fatigue damage under extreme working conditions of each fatigue hot spot in the monitoring time are added respectively to determine the cumulative fatigue damage of each fatigue hot spot;

[0180] It should be noted that based on the above basis, the fatigue damage of the kth fatigue hot spot during the service period is is:

[0181] ;

[0182] Further, in combination with the fatigue damage in the monitoring time, the cumulative fatigue damage of the kth fatigue hot spot is is:

[0183] ;

[0184] Step S55, based on the cumulative fatigue damage of each fatigue hot spot, the annual fatigue damage and the remaining fatigue life of each fatigue hot spot are calculated.

[0185] It should be noted that assuming that the fatigue damage caused by waves of the kth fatigue hot spot is the same every year, the annual fatigue damage of the kth fatigue hot spot is is:

[0186] ;

[0187] wherein, T is the service period before stress monitoring of the floating platform, and the unit is year; t is the stress monitoring time of the floating platform, and the unit is year.

[0188] Further, the remaining fatigue life of the kth fatigue hot spot (unit: year) is:

[0189] ;

[0190] Exemplarily, the fatigue hot spot accumulates fatigue damage from the fatigue damage during monitoring, the fatigue damage caused by long-term environmental load in the service period and the fatigue damage caused by extreme environmental load in the service period. The stress response prediction data of the fatigue hot spot during monitoring is rainflow counted, and the fatigue damage in this period is calculated in combination with the S-N curve. The S-N curve of DNV-1 is adopted, and the curve parameters are as shown in Table 3. It is calculated that the fatigue damage degree of the fatigue hot spot during monitoring is 1.37 x 10 -16 .

[0191] Table 3 DNV-1 S-N curve parameters

[0192]

[0193] Further, the South China Sea wave scatter diagram and the JONSWAP wave spectrum are adopted, it is assumed that the service life of the floating platform is 10 years, and the probabilities of each wave direction are the same, wherein the parameters of the South China Sea wave scatter diagram are shown in Table 4; at the same time, the extreme working condition encountered by the platform is the extreme working condition of 50 years, the effective wave height is 12.6 m, the effective period is 24.1 s, the extreme working condition duration is 3 days, and the probabilities of each wave direction are the same. As shown in Table 5, the fatigue damage caused by long-term environmental load and extreme environmental load in the service period is 0.43115, respectively. The fatigue damage degree of the fatigue hot spot per year is 0.043, and the remaining fatigue life is 12.77 years.

[0194] Table 4 Parameters of South China Sea wave scatter diagram

[0195]

[0196] Table 5 Fatigue damage and remaining fatigue life of fatigue hot spot

[0197]

[0198] As a comparison of technical effects, for the purpose of evaluating the fatigue damage of a floating platform, a commonly used fatigue monitoring technology monitors stress responses under different sea conditions by arranging a limited number of sensors, obtains hotspot stress data by linear extrapolation, and then uses the rainflow counting method and S-N curve to perform fatigue analysis. However, the main dimension of the floating platform is large, and the number of fatigue hotspots is large. At the same time, due to the high cost of arrangement and the limitation of physical space, some fatigue hotspots do not have the condition to directly monitor the stress, and the existing fatigue monitoring technology has high cost and limited coverage. The main dimension of the floating platform is large, and the number of fatigue hotspots is large. At the same time, due to the limitation of the structure of the floating platform, most of the areas do not have the condition to arrange sensors, so this method cannot comprehensively evaluate the fatigue damage of the floating platform. At the same time, the existing fatigue damage evaluation method combining stress monitoring and finite element calculation has limited precision and needs to be improved. The fatigue damage evaluation method of the floating platform based on the overall stress response combines stress monitoring and finite element calculation, and establishes two databases: one is a database with the stress response of the overall stress monitoring point as the input and the wave parameter as the output, and the other is a database with the wave parameter as the input and the fatigue damage rate of the fatigue hotspot as the output. The method calculates the cumulative fatigue damage value of the fatigue hotspot according to the overall stress response monitoring data and the database. However, this method calculates the fatigue damage of the fatigue hotspot based on the fatigue spectrum analysis method, and therefore cannot consider nonlinear, low-frequency fatigue stress and other factors, so the precision is still insufficient compared with the time-domain fatigue calculation method. In addition, the existing fatigue damage evaluation method of the floating platform does not consider the cumulative fatigue damage in the service life, and does not consider the fatigue damage caused by extreme working conditions in the service life, so it cannot accurately evaluate the remaining fatigue life of the floating platform. With climate warming and the greenhouse effect, extreme working conditions such as typhoons and tsunamis are more frequent, and the probability of occurrence of extreme working conditions is significantly increased. If the fatigue damage caused by extreme working conditions is not considered, the predicted fatigue life will be larger, and the safety margin will be insufficient.

[0199] Therefore, the traditional stress monitoring method cannot comprehensively and accurately evaluate the fatigue damage state of the structure, and a low-cost and accurate fatigue damage evaluation method of the floating platform is needed to solve the problem of limited coverage of the traditional fatigue monitoring method.

[0200] In view of the above problems, the present application provides a fatigue damage evaluation method of a floating platform, which aims to overcome the problems of high cost and limited application range of the fatigue monitoring method, and improve the precision of the remaining fatigue life evaluation. Specifically, please refer to Figure 101) Machine learning based fatigue hot spot stress inversion: Using machine learning techniques, fatigue damage at fatigue hot spots is predicted based on stress time histories at limited monitoring points, thereby expanding the coverage of fatigue monitoring. By establishing a stress time history database for monitoring points and fatigue hot spots through time-domain finite element calculations, a prediction model is further established using machine learning algorithms, with monitoring point stress time histories as input and fatigue hot spot stress time histories as output. Combined with the rainflow counting method and selected S-N curves, the cumulative fatigue damage of fatigue hot spots during stress monitoring is calculated, and a comprehensive assessment of fatigue hot spots is achieved. 2) Improve fatigue damage assessment accuracy: Using time-domain finite element calculation method, fully considering nonlinear, low-frequency fatigue stress and other factors, the fatigue assessment accuracy is significantly improved. Compared with the traditional frequency-domain fatigue spectrum analysis method, time-domain finite element calculation can more accurately capture the characteristics of complex stress response, thereby providing higher reliability for fatigue damage assessment. 3) Accurate prediction of remaining fatigue life: For the fatigue damage of the floating platform during the service life, the influence of long-term environmental load and extreme environmental load is considered respectively, and the remaining fatigue life is accurately predicted. By dividing the fatigue damage of the floating platform during the service life into long-term environmental load and extreme environmental load, the cumulative fatigue damage of the floating platform under the current state is comprehensively evaluated by analyzing and combining the fatigue damage during stress monitoring predicted by machine learning. On this basis, the remaining fatigue life is further predicted, providing a scientific basis for the safe operation and maintenance decision of the floating platform.

[0201] In summary, the present application proposes an intelligent prediction model (fatigue hot spot stress response prediction model) for ocean platform structures with sensors installed. This method realizes spatial correlation mapping of the structure stress field through the construction of a multi-layer perception neural network, and realizes non-measurement point stress prediction by deeply mining the nonlinear correlation characteristics between measurement points, effectively solving the technical problem of insufficient prediction accuracy of traditional interpolation methods in complex marine engineering environments. A double-hidden layer network architecture is designed for the characteristics of ocean platform structures, effectively controlling the model complexity while ensuring prediction accuracy. At the same time, the present application combines stress monitoring and time-domain finite element calculation methods, and considers nonlinear, low-frequency fatigue stress and other factors, improving the accuracy of the traditional combination method of stress monitoring and frequency-domain finite element calculation. In addition, the present application also considers the fatigue damage caused by long-term and extreme environmental loads during the service life of the floating platform, overcomes the shortcomings of methods that only consider the fatigue damage caused by long-term environmental loads of the floating platform, and accurately predicts the remaining fatigue life of the floating platform.

[0202] In the embodiment of the present application, the present application provides a floating platform fatigue damage evaluation method, first, the wave scatter diagram of the working sea area of the floating platform is obtained, and the corresponding floating platform overall finite element model of the floating platform is established; then, based on the wave scatter diagram and a plurality of preset wave spectra, the long-term sea conditions in the wave scatter diagram are discretized, and a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model are determined; a plurality of fatigue hot spots are determined by using a preset fatigue hot spot analysis method according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset floating platform loading conditions and the plurality of short-term sea conditions corresponding to each local structure for fatigue hot spot analysis of the floating platform overall finite element model; a fatigue hot spot stress response prediction model is constructed according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum and a plurality of stress monitoring points of the floating platform by using a time domain finite element method and a machine learning algorithm; finally, based on a three-point rain flow counting method and a time domain finite element method, a fatigue hot spot stress response prediction model is used to generate fatigue damage results of each fatigue hot spot according to each stress monitoring point, corresponding extreme environmental load conditions of the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea conditions corresponding to each local structure, and a preset stress-life curve; based on the above scheme, a fatigue hot spot stress response prediction model is established by using a machine learning algorithm, and the fatigue damage results of each fatigue hot spot in the floating platform are generated by combining a three-point rain flow counting method, a preset stress-life curve, thereby realizing comprehensive evaluation of the fatigue damage of the floating platform.

[0203] Please refer to Figure 11 , Figure 11 The structural block diagram of a floating platform fatigue damage evaluation device provided for the embodiment of the present application.

[0204] The floating platform fatigue damage evaluation device provided by the present application comprises:

[0205] The acquisition module 1101 is configured to acquire the wave scatter diagram of the working sea area of the floating platform, and establish the corresponding floating platform overall finite element model of the floating platform;

[0206] The determination module 1102 is configured to discretize the long-term sea conditions in the wave scatter diagram based on the wave scatter diagram and a plurality of preset wave spectra, and determine a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model;

[0207] The analysis module 1103 is configured to determine a plurality of fatigue hot spots by using a preset fatigue hot spot analysis method according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset floating platform loading conditions and the plurality of short-term sea conditions corresponding to each local structure for fatigue hot spot analysis of the floating platform overall finite element model;

[0208] The construction module 1104 is configured to construct a fatigue hot spot stress response prediction model according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum, and a plurality of stress monitoring points of the floating platform by using a time domain finite element method and a machine learning algorithm;

[0209] The evaluation module 1105 is configured to generate fatigue damage results of each fatigue hot spot by using the fatigue hot spot stress response prediction model according to each stress monitoring point, an extreme environmental load condition corresponding to the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea states corresponding to each local structure, and a preset stress-life curve based on a three-point rainflow counting method and a time domain finite element method.

[0210] Further, the preset fatigue hot spot analysis method includes an offshore mobile platform classification specification, a stress response under a dangerous working condition, and a fatigue spectrum analysis method. The determination module 1102 includes:

[0211] A first sub-module is configured to analyze the overall finite element model of the floating platform based on the offshore mobile platform classification specification, and determine a plurality of fatigue hot spots;

[0212] A second sub-module is configured to analyze the overall finite element model of the floating platform based on the stress response under the dangerous working condition, and determine a plurality of fatigue hot spots;

[0213] A third sub-module is configured to analyze the overall finite element model of the floating platform by using the fatigue spectrum analysis method according to a plurality of preset regular wave sea states, a wave scatter diagram, a plurality of preset floating platform loading conditions, and a plurality of short-term sea states corresponding to each local structure, and determine a plurality of fatigue hot spots.

[0214] Further, the third sub-module is specifically configured to:

[0215] construct a plurality of stress transfer functions corresponding to each local structure of the overall finite element model of the floating platform under each preset regular wave sea state and each preset floating platform loading condition;

[0216] determine wave spectra of each local structure under each short-term sea state based on the plurality of short-term sea states corresponding to each local structure;

[0217] calculate stress energy spectrum densities of each local structure under each short-term sea state according to the plurality of stress transfer functions corresponding to each local structure and the wave spectra of each local structure under each short-term sea state;

[0218] determine a joint probability of a significant wave height and an above-zero-crossing period of each short-term sea state based on the wave scatter diagram;

[0219] calculate a total fatigue life of each local structure according to the stress energy spectrum densities of each local structure under each short-term sea state and the joint probability of the significant wave height and the above-zero-crossing period of each short-term sea state.

[0220] ranking the total fatigue life of each local structure in ascending order, and selecting the local structure corresponding to the total fatigue life of the first preset number of positions as the fatigue hot spot.

[0221] Further, the construction module 1104 is specifically configured to:

[0222] adopting the time domain finite element method to output the simulated stress response time history data of the plurality of stress monitoring points and the simulated stress response time history data of the plurality of fatigue hot spots according to the plurality of preset floating platform loading conditions, the wave characteristic parameters corresponding to the plurality of preset wave spectra, and the positions of the plurality of stress monitoring points and the plurality of fatigue hot spots;

[0223] constructing a fatigue hot spot stress response prediction model based on a machine learning algorithm, taking the simulated stress response time history data of the plurality of stress monitoring points as input, and taking the simulated stress response time history data of the plurality of fatigue hot spots as output.

[0224] Further, the fatigue damage result includes annual fatigue damage and remaining fatigue life; the evaluation module 1105 includes:

[0225] The fourth submodule is configured to calculate the fatigue damage of each fatigue hot spot within the monitoring time based on the three-point rainflow counting method, the fatigue hot spot stress response prediction model, the monitoring stress response time history data corresponding to each stress monitoring point, and the preset stress-life curve.

[0226] The fifth submodule is configured to calculate the fatigue damage caused by long-term environmental load of each fatigue hot spot by adopting the three-point rainflow counting method and the time domain finite element method according to the preset stress-life curve, the plurality of preset floating platform loading conditions, and the plurality of short-term sea conditions corresponding to each local structure.

[0227] The sixth submodule is configured to calculate the fatigue damage of each fatigue hot spot under extreme conditions by adopting the three-point rainflow counting method and the time domain finite element method according to the extreme environmental load conditions corresponding to the floating platform, the plurality of preset floating platform loading conditions, and the preset stress-life curve.

[0228] The seventh submodule is configured to add the fatigue damage within the monitoring time, the fatigue damage caused by long-term environmental load, and the fatigue damage under extreme conditions of each fatigue hot spot respectively to determine the cumulative fatigue damage of each fatigue hot spot.

[0229] The eighth submodule is configured to calculate the annual fatigue damage and the remaining fatigue life of each fatigue hot spot based on the cumulative fatigue damage of each fatigue hot spot.

[0230] Further, the fourth submodule is specifically configured to:

[0231] The monitoring stress response time series data corresponding to each stress monitoring point is taken as an input of a fatigue hot spot stress response prediction model, and first stress response time series data of a plurality of fatigue hot spots are output;

[0232] The first stress time series data of the plurality of fatigue hot spots are analyzed by using a three-point rain flow counting method to determine a plurality of first stress cycle amplitudes and stress range cycle numbers corresponding to each first stress cycle amplitude;

[0233] According to the pre-set stress-life curve and the plurality of first stress cycle amplitudes, average numbers of fatigue damage of the structure corresponding to each first stress cycle amplitude are determined.

[0234] According to the average numbers of fatigue damage of the structure corresponding to each first stress cycle amplitude and the stress range cycle numbers, fatigue damages of each fatigue hot spot in the monitoring time are calculated.

[0235] Further, the fifth sub-module is specifically configured to:

[0236] The second stress time series data of the plurality of fatigue hot spots are determined by using a time-domain finite element method according to a plurality of short-term sea states corresponding to each local structure and a plurality of pre-set floating platform loading conditions.

[0237] The second stress time series data of the plurality of fatigue hot spots are analyzed by using a three-point rain flow counting method to determine a plurality of second stress cycle amplitudes and stress range cycle numbers corresponding to each second stress cycle amplitude.

[0238] According to the pre-set stress-life curve and the plurality of second stress cycle amplitudes, stress cycle numbers required for fatigue damage of the structure corresponding to each second stress cycle amplitude are determined.

[0239] According to the stress cycle numbers required for fatigue damage of the structure corresponding to each second stress cycle amplitude and the stress range cycle numbers, fatigue damages of each fatigue hot spot caused by long-term environmental loads are calculated.

[0240] Further, the sixth sub-module is specifically configured to:

[0241] The third stress time series data of the plurality of fatigue hot spots are determined by using a time-domain finite element method according to extreme environmental load conditions corresponding to the floating platform and a plurality of pre-set floating platform loading conditions.

[0242] The third stress time series data of the plurality of fatigue hot spots are analyzed by using a three-point rain flow counting method to determine a plurality of third stress cycle amplitudes and stress range cycle numbers corresponding to each third stress cycle amplitude.

[0243] According to the pre-set stress-life curve and the plurality of third stress cycle amplitudes, stress cycle numbers required for fatigue damage of the structure corresponding to each third stress cycle amplitude are determined.

[0244] According to the stress cycle number and stress range cycle number required for the structure corresponding to each third stress cycle amplitude to occur fatigue failure, the fatigue damage of each fatigue hot spot under the extreme working condition is calculated.

[0245] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device, module and sub-module can refer to the corresponding process in the foregoing method embodiments, and will not be described here.

[0246] The embodiment of the present application also provides a computer device, comprising a memory and a processor, the memory stores a computer program; the computer program is executed by the processor, so that the processor executes the steps of the fatigue damage evaluation method of the floating platform as in any one of the above embodiments.

[0247] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of fatigue damage assessment for a floating platform, the method comprising: The method comprises the following steps: obtain a wave scatter diagram of a working sea area of a floating platform, and establish a corresponding overall finite element model of the floating platform; discretize long-term sea conditions in the wave scatter diagram based on the wave scatter diagram and a plurality of preset wave spectra, and determine a plurality of short-term sea conditions corresponding to each local structure in the overall finite element model of the floating platform; perform fatigue hot spot analysis on the overall finite element model of the floating platform according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset loading conditions of the floating platform, and the plurality of short-term sea conditions corresponding to each local structure by using a preset fatigue hot spot analysis method, and determine a plurality of fatigue hot spots; construct a fatigue hot spot stress response prediction model according to each fatigue hot spot, each preset loading condition of the floating platform, each preset wave spectrum, and a plurality of stress monitoring points of the floating platform by using a time-domain finite element method and a machine learning algorithm, which comprises the following steps: output simulated stress response time history data of the plurality of stress monitoring points and simulated stress response time history data of the plurality of fatigue hot spots according to each preset loading condition of the floating platform, wave characteristic parameters corresponding to each preset wave spectrum, the plurality of stress monitoring points, and the positions of the plurality of fatigue hot spots by using the time-domain finite element method; construct a fatigue hot spot stress response prediction model based on the machine learning algorithm, which takes the simulated stress response time history data of the plurality of stress monitoring points as input and takes the simulated stress response time history data of the plurality of fatigue hot spots as output; generate fatigue damage results of each fatigue hot spot according to each stress monitoring point, extreme environmental load conditions corresponding to the floating platform, a plurality of preset loading conditions of the floating platform, a plurality of short-term sea conditions corresponding to each local structure, and a preset stress-life curve by using the fatigue hot spot stress response prediction model based on a three-point rainflow counting method and the time-domain finite element method.

2. The floating platform fatigue damage assessment method of claim 1, wherein, The preset fatigue hot spot analysis method comprises offshore mobile platform classification rules, stress response under dangerous working conditions, and fatigue spectrum analysis method; the fatigue hot spot analysis on the overall finite element model of the floating platform according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset loading conditions of the floating platform, and a plurality of short-term sea conditions corresponding to each local structure by using the preset fatigue hot spot analysis method to determine a plurality of fatigue hot spots comprises the following steps: analyze the overall finite element model of the floating platform based on the offshore mobile platform classification rules to determine a plurality of fatigue hot spots; analyze the overall finite element model of the floating platform based on the stress response under dangerous working conditions to determine a plurality of fatigue hot spots; analyze the overall finite element model of the floating platform according to a plurality of the preset regular wave sea conditions, the wave scatter diagram, a plurality of preset loading conditions of the floating platform, and a plurality of short-term sea conditions corresponding to each local structure by using the fatigue spectrum analysis method to determine a plurality of fatigue hot spots.

3. The floating platform fatigue damage assessment method of claim 2, wherein, The fatigue spectrum analysis method includes the following steps: The stress transfer function of each local structure of the overall finite element model of the floating platform is constructed under each preset regular wave sea state and each preset floating platform loading condition, and a plurality of stress transfer functions corresponding to each local structure is generated; Based on the plurality of short-term sea states corresponding to each local structure, the wave spectrum of each local structure under each short-term sea state is determined; According to the plurality of stress transfer functions corresponding to each local structure and the wave spectrum of each local structure under each short-term sea state, the stress energy spectrum density of each local structure under each short-term sea state is calculated; Based on the wave scatter diagram, the joint probability of the significant wave height and the over-zero period of each short-term sea state is determined; According to the stress energy spectrum density of each local structure under each short-term sea state, the joint probability of the significant wave height and the over-zero period of each short-term sea state, the total fatigue life of each local structure is calculated; The total fatigue life of each local structure is sorted in ascending order, and the local structure corresponding to the total fatigue life of the first preset number of positions is selected as the fatigue hot spot.

4. The floating platform fatigue damage assessment method of claim 1, wherein, The fatigue damage results include annual fatigue damage and remaining fatigue life; based on the three-point rainflow counting method and the time-domain finite element method, the fatigue hot spot stress response prediction model is used to generate the fatigue damage results of each fatigue hot spot according to the stress monitoring points, the extreme environmental load conditions corresponding to the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea states corresponding to each local structure, and a preset stress-life curve, including: Based on the three-point rainflow counting method, the fatigue hot spot stress response prediction model is used to calculate the fatigue damage of each fatigue hot spot within the monitoring time according to the monitoring stress response time history data corresponding to each stress monitoring point and the preset stress-life curve; Based on the three-point rainflow counting method and the time-domain finite element method, the fatigue damage of each fatigue hot spot caused by long-term environmental load is calculated according to the preset stress-life curve, a plurality of preset floating platform loading conditions, and a plurality of short-term sea states corresponding to each local structure; Based on the three-point rainflow counting method and the time-domain finite element method, the fatigue damage of each fatigue hot spot under extreme conditions is calculated according to the extreme environmental load conditions corresponding to the floating platform, a plurality of preset floating platform loading conditions, and the preset stress-life curve; The fatigue damage of each fatigue hot spot within the monitoring time, the fatigue damage caused by long-term environmental load, and the fatigue damage under extreme conditions are added respectively to determine the cumulative fatigue damage of each fatigue hot spot; Based on the cumulative fatigue damage of each fatigue hot spot, the annual fatigue damage and the remaining fatigue life of each fatigue hot spot are calculated.

5. The floating platform fatigue damage assessment method of claim 4, wherein, The three-point rainflow counting method is used to analyze the first stress time history data of the plurality of fatigue hot spots, a plurality of first stress cycle amplitudes and a stress range cycle number corresponding to each of the first stress cycle amplitudes are determined. The three-point rainflow counting method is used to analyze the first stress time history data of the plurality of fatigue hot spots, a plurality of first stress cycle amplitudes and a stress range cycle number corresponding to each of the first stress cycle amplitudes are determined. According to the pre-stress-life curve and the plurality of first stress cycle amplitudes, the average number of stress cycles required for the structure to fail due to fatigue corresponding to each of the first stress cycle amplitudes is determined. According to the average number of stress cycles required for the structure to fail due to fatigue corresponding to each of the first stress cycle amplitudes and the stress range cycle number, the fatigue damage of each of the fatigue hot spots within the monitoring time is calculated. The three-point rainflow counting method and the time-domain finite element method are used to calculate the fatigue damage of each of the fatigue hot spots caused by long-term environmental load according to the pre-stress-life curve, a plurality of pre-stored floating platform loading conditions, and a plurality of short-term sea conditions corresponding to each of the local structures, including:

6. The floating platform fatigue damage assessment method of claim 4, wherein, The time-domain finite element method is used to determine the second stress time history data of the plurality of fatigue hot spots according to a plurality of short-term sea conditions corresponding to each of the local structures and a plurality of pre-stored floating platform loading conditions. The three-point rainflow counting method is used to analyze the second stress time history data of the plurality of fatigue hot spots, a plurality of second stress cycle amplitudes and a stress range cycle number corresponding to each of the second stress cycle amplitudes are determined. According to the pre-stress-life curve and the plurality of second stress cycle amplitudes, the stress cycle number required for the structure to fail due to fatigue corresponding to each of the second stress cycle amplitudes is determined. According to the stress cycle number required for the structure to fail due to fatigue corresponding to each of the second stress cycle amplitudes and the stress range cycle number, the fatigue damage of each of the fatigue hot spots caused by long-term environmental load is calculated. The three-point rainflow counting method and the time-domain finite element method are used to calculate the fatigue damage of each of the fatigue hot spots under extreme conditions according to the extreme environmental load conditions corresponding to the floating platform, a plurality of pre-stored floating platform loading conditions, and the pre-stress-life curve, including:

7. The floating platform fatigue damage assessment method of claim 4, wherein, The time-domain finite element method is used to determine the third stress time history data of the plurality of fatigue hot spots according to the extreme environmental load conditions corresponding to the floating platform and a plurality of pre-stored floating platform loading conditions. The three-point rainflow counting method is used to analyze the third stress time history data of the plurality of fatigue hot spots, a plurality of third stress cycle amplitudes and a stress range cycle number corresponding to each of the third stress cycle amplitudes are determined. According to the pre-stress-life curve and the plurality of third stress cycle amplitudes, the stress cycle number required for the structure to fail due to fatigue corresponding to each of the third stress cycle amplitudes is determined. ​ According to the stress cycle number and stress range cycle number required for fatigue failure of each structure corresponding to each third stress cycle amplitude, the fatigue damage of each fatigue hot spot under the extreme working condition is calculated.

8. A floating platform fatigue damage assessment apparatus, characterized by, The method comprises the following steps: An acquisition module is configured to acquire a wave scatter diagram of a working sea area of a floating platform and establish a floating platform overall finite element model corresponding to the floating platform. A determination module is configured to disperse long-term sea conditions in the wave scatter diagram based on the wave scatter diagram and a plurality of preset wave spectra, and determine a plurality of short-term sea conditions corresponding to each local structure in the floating platform overall finite element model. An analysis module is configured to perform fatigue hot spot analysis on the floating platform overall finite element model according to a plurality of preset regular wave sea conditions, the wave scatter diagram, a plurality of preset floating platform loading conditions, and a plurality of short-term sea conditions corresponding to each local structure, by using a preset fatigue hot spot analysis method, and determine a plurality of fatigue hot spots. A construction module is configured to construct a fatigue hot spot stress response prediction model according to each fatigue hot spot, each preset floating platform loading condition, each preset wave spectrum, and a plurality of stress monitoring points of the floating platform, by using a time-domain finite element method and a machine learning algorithm. An evaluation module is configured to generate fatigue damage results of each fatigue hot spot based on a three-point rain flow counting method and the time-domain finite element method, by using the fatigue hot spot stress response prediction model according to each stress monitoring point, extreme environmental load conditions corresponding to the floating platform, a plurality of preset floating platform loading conditions, a plurality of short-term sea conditions corresponding to each local structure, and a preset stress-life curve. The construction module is specifically configured to: output simulation stress response time history data of a plurality of stress monitoring points and simulation stress response time history data of a plurality of fatigue hot spots, by using a time-domain finite element method according to each preset floating platform loading condition, wave characteristic parameters corresponding to each preset wave spectrum, a plurality of stress monitoring points, and positions of a plurality of fatigue hot spots; construct a fatigue hot spot stress response prediction model based on a machine learning algorithm, wherein the fatigue hot spot stress response prediction model takes simulation stress response time history data of a plurality of stress monitoring points as input and takes simulation stress response time history data of a plurality of fatigue hot spots as output.

9. A computer device, comprising: The method comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the floating platform fatigue damage evaluation method according to any one of claims 1-7.

Images