Real-time simulation platform for FPSO riser support system based on Modelica

Abstract

This invention discloses a real-time simulation platform for an FPSO riser support system based on Modelica, belonging to the field of intelligent simulation. It includes modules for requirement definition, data loading, environment simulation, riser support modeling, system verification, simulation calculation, optimization scheduling, evaluation and analysis, control suggestions, real-time visualization, storage and backtracking, and feedback adjustment. This invention can globally search high-dimensional nonlinear spaces to find better solutions, avoid premature convergence, improve the stability of optimization results, ensure that parameter configurations maintain optimal performance under varying operating conditions, enhance the intelligence and adaptability of operating strategies, ensure that the riser support system is always in the optimal control state under different operating conditions, achieve high efficiency in multi-objective optimization, and help find the optimal balance between reducing vibration, reducing wear, and extending equipment life, thereby achieving a dual improvement in economy and safety.

Description

Technical Field

[0001] The present invention relates to the field of intelligent simulation, and in particular to a real-time simulation platform for an FPSO riser support system based on Modelica. Background Art

[0002] Floating Production Storage and Offloading (FPSO) is an important facility for offshore oil and gas production and is widely used in the exploitation, storage and transportation of deep-sea oil fields. The riser support system of FPSO plays a key role in connecting the underwater wellhead equipment with the production and storage of FPSO. Its reliability and performance directly affect the operating efficiency and safety of the system. However, the riser support system is usually faced with dynamic loads in complex and changeable marine environments (such as wind, waves, currents, etc.), which may cause fatigue damage, vibration instability and other problems, thereby threatening the safety of the entire production system. Traditional design and analysis methods often rely on offline simulation and static optimization, which are difficult to adapt to the needs of real-time dynamic changes. Therefore, it is of great significance to develop an efficient, real-time, and global optimization capable real-time simulation platform for FPSO riser support systems based on Modelica.

[0003] The existing real-time simulation platform for FPSO riser support system cannot globally search the high-dimensional nonlinear space, and is prone to premature convergence, which reduces the stability of the optimization results. In addition, the existing real-time simulation platform for FPSO riser support system cannot ensure that the riser support system is always in the optimal control state under different working conditions, which is not conducive to finding the best balance between reducing vibration, reducing wear and extending equipment life. Therefore, we propose a real-time simulation platform for FPSO riser support system based on Modelica. Summary of the invention

[0004] The purpose of the present invention is to solve the defects in the prior art and to propose a real-time simulation platform for an FPSO riser support system based on Modelica.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The real-time simulation platform of the FPSO riser support system based on Modelica includes a requirement definition module, a data loading module, an environmental simulation module, a riser support modeling module, a system verification module, a simulation calculation module, an optimization scheduling module, an evaluation and analysis module, a control suggestion module, a real-time visualization module, a storage backtracking module, and a feedback adjustment module;

[0007] The requirement definition module is used for user input of operation requirements and converting the requirements into parseable tasks;

[0008] The data loading module is used to load various basic data groups including FPSO platform structural parameters, riser material properties, support system design standards and historical operation data;

[0009] The environment simulation module is used to simulate the environment through random ocean processes and generate simulation scenario input;

[0010] The riser support modeling module is used to build a dynamic model of the riser support system based on Modelica;

[0011] The system verification module is used to verify the accuracy of the dynamic model based on historical data and experimental data, and to identify existing modeling errors and automatically correct them;

[0012] The simulation calculation module is used to calculate the response of the dynamic model under actual environmental conditions;

[0013] The optimization scheduling module is used to globally optimize the parameter configuration of the riser support system;

[0014] The evaluation and analysis module is used to comprehensively evaluate performance and identify potential risks;

[0015] The control suggestion module is used to analyze the impact of different operation strategies on system performance and generate optimal control suggestions;

[0016] The real-time visualization module is used to display the state changes of the FPSO riser support system in real time using 3D visualization technology;

[0017] The storage backtracking module is used to classify and store various data generated during the simulation process, and supports fast backtracking and re-analysis of the data;

[0018] The feedback adjustment module is used to receive adjustment instructions from users or control systems, and dynamically adjust modeling parameters or optimization targets.

[0019] As a further solution of the present invention, the specific steps of generating the simulation scene input by the environment simulation module are as follows:

[0020] S1.1: The wave, wind speed and tidal current environmental factors in the ocean environment are parameterized through the Pierson-Moskowitz spectrum to generate a wave spectrum model, and the value range and probability distribution of each environmental factor are obtained based on the wave spectrum model;

[0021] S1.2: Divide each group of environmental factors into multiple equal probability intervals, and set the boundary points of each equal probability interval through the cumulative distribution function. Then, for each environmental factor, according to the multiple equal probability intervals, randomly select an environmental factor from each interval, and repeat the extraction until the preset value is reached;

[0022] S1.3: Construct the corresponding LHS matrix based on the extracted groups of environmental factors. Randomly arrange the interval order in multiple intervals of each factor. Then use the distribution function of the environmental factor to map the standardized values ​​in the LHS matrix to the actual physical space. After the mapping is completed, integrate all environmental factors to generate the final environmental condition sample set.

[0023] S1.4: Based on the evaluation indicators of the importance of working conditions, economy and probability of occurrence of environmental conditions, a weighted evaluation indicator matrix is ​​constructed, and the weight of each group of evaluation indicators is calculated using the hierarchical analysis method. Based on the environmental condition samples and the weight matrix, a comprehensive score is calculated, and multiple groups of samples with the highest scores are selected as the environmental condition combination to generate simulation scenario input.

[0024] As a further solution of the present invention, the specific calculation formula of the Pierson-Moskowitz spectrum described in S1.1 is as follows:

[0025] ;

[0026] In the formula, represents the wave energy spectral density; and Represent the empirical coefficients respectively; represents the acceleration due to gravity; Represents significant wave height.

[0027] As a further solution of the present invention, the riser support modeling module constructs a dynamic model of the riser support system in the following specific steps:

[0028] S2.1: Decompose the riser support system into multiple subsystems and components, and collect and set the physical properties and interactions of each subsystem. Then, establish the equations of motion of the riser and support system based on Newtonian mechanics and Lagrangian dynamics;

[0029] S2.2: Apply spring-damper models at the support points to describe the interaction between the riser and the support structure. Then deploy and implement the physical models of each subsystem in the Modelica software, input the material properties, geometric parameters and boundary conditions of each subsystem model, and use the fluid-structure interaction model to simulate the force of the fluid on the structure;

[0030] S2.3: Integrate the riser, support structure, and fluid-structure interaction models in the Modelica software, configure the initial conditions and simulation parameters, and configure the simulation step size and real-time calculation framework.

[0031] As a further solution of the present invention, the specific steps of global optimization of the optimization scheduling module are as follows:

[0032] S3.1: Maximizing the stability of the riser, minimizing the vibration amplitude, and minimizing the cost of the support system are taken as optimization objectives, and the performance indicators of the riser support system are converted into objective functions. The objective function constraints are set based on the parameter range, and a group of population individuals are randomly generated, and each individual represents a set of parameter configurations of the riser support system;

[0033] S3.2: Obtain the comprehensive score of each individual in the population through the objective function, take the decision plan with the highest comprehensive score as the optimal individual, set a set of coefficient vectors, and generate a random number between 0 and 1 in each round of iteration. If the generated random number is greater than the preset probability parameter, calculate the coefficient and step size of the control position update based on the coefficient vector, and judge whether the remaining individuals are shrinking around the optimal solution according to the size of the direction;

[0034] S3.3: If the coefficient is less than 1, it means that the remaining individuals surround the optimal individual, and the positions of the remaining individuals are updated according to the optimal individual, that is, the parameter configuration of each individual is adjusted. If the coefficient is ≥ 1, it means that the remaining individuals are far away from the optimal individual. Through random search, random positions are selected in the population space, and the positions of the remaining individuals are updated. After each iteration, the coefficient vector is updated based on the linear decreasing rule.

[0035] S3.4: If the generated random number is less than or equal to the preset probability parameter, the distance between the positions of the remaining individuals in the population and the position of the optimal individual is calculated, and the movement law of each individual along the spiral trajectory approaching the optimal individual is simulated through the spiral motion formula to update the individual position;

[0036] S3.5: Repeat the optimal individual selection and iterative update of the position until the comprehensive score change value converges to the preset threshold range, then compare the comprehensive scores of individuals in each group, and output the individual with the highest comprehensive evaluation score as the optimal parameter configuration of the system, and adjust the simulation parameters of the current support system dynamic model based on the optimal parameter configuration.

[0037] As a further solution of the present invention, the specific calculation formula of the objective function described in S3.1 is as follows:

[0038] ;

[0039] In the formula, Representative Parameter configuration of group individuals The fitness function value of Represents the total duration of the simulation; Representative time steps; Representative In time steps, based on parameter configuration The riser vibration response; Represents the target vibration value; A penalty term representing the cost.

[0040] As a further solution of the present invention, the control suggestion module generates the optimal control suggestion in the following specific steps:

[0041] S4.1: Collect all states and operation strategies of the riser support system, and establish the corresponding state space and action space, then discretize the continuous state variables and operation strategies of the system in the state space and action space, and calculate the probability of the system transferring from any state to the next state under the action of the operation strategy through simulation or statistical data;

[0042] S4.2: Set a reward value for each state-action strategy pair to obtain the impact of the action strategy on the system performance. In the state space, assign a random action strategy to each state to initialize the strategy. Update the value function of each state according to the control instructions executed by the current strategy through the Bellman equation.

[0043] S4.4: Use a recursive calculation method to iteratively update the value function step by step until the change in the value function of all states is less than the preset threshold. Compare the strategies before and after the update. If the two are the same in all states, the strategy is considered to have converged; otherwise, use the new strategy to continue to perform the strategy evaluation and improvement steps until the strategy no longer changes in all states. Then, in each state, select the operating strategy that maximizes the value function and use it as the new operating strategy for the FPSO riser support system.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1. The present invention takes maximizing the stability of the riser, minimizing the vibration amplitude and minimizing the cost of the support system as optimization goals, and converts the performance index of the riser support system into an objective function. The objective function constraint conditions are set based on the parameter range, and a group of population individuals are randomly generated, and each individual represents a set of parameter configurations of the riser support system. The comprehensive score of each individual in the population is obtained through the objective function, and the decision plan with the highest comprehensive score is taken as the optimal individual. A group of coefficient vectors are set, and a random number between 0 and 1 is generated in each round of iteration. If the generated random number is greater than a preset probability parameter, the coefficient and step size of the control position update are calculated according to the coefficient vector, and the remaining individuals are controlled to shrink around the optimal solution according to the size of the direction. After each iteration, the optimal solution is obtained based on the linear recursive The coefficient vector is updated according to the rule of subtraction. If the generated random number is less than or equal to the preset probability parameter, the distance between the positions of the remaining individuals in the population and the position of the optimal individual is calculated, and the motion law of each individual approaching the optimal individual along the spiral trajectory is simulated through the spiral motion formula, and the individual position is updated. The optimal individual selection and iterative update of the position are repeated until the change value of the comprehensive score converges to the preset threshold range. After that, the comprehensive scores of the individuals in each group are compared, and the individual with the highest comprehensive evaluation score is output as the optimal parameter configuration of the system. Based on the optimal parameter configuration, the simulation parameters of the dynamic model of the current support system are adjusted. It can globally search the high-dimensional nonlinear space, find a better solution, avoid premature convergence, improve the stability of the optimization results, and ensure that the parameter configuration always maintains the best performance under variable working conditions.

[0046] 2. The present invention collects all states and operation strategies of the riser support system, and establishes corresponding state space and action space, then discretizes the continuous state variables and operation strategies of the system in the state space and action space, calculates the probability of the system transferring from any state to the next state under the action of the operation strategy through simulation or statistical data, sets a reward value for each state-operation strategy pair to obtain the impact of the operation strategy on the system performance, assigns a random operation strategy to each state in the state space to initialize the strategy, updates the value function of each state according to the control instructions executed by the current strategy through the Bellman equation, and uses a recursive calculation method to gradually iterate and update the value function until all When the value function change of the state is less than the preset threshold, the strategies before and after the update are compared. If the two are the same in all states, the strategy is considered to have converged; otherwise, the new strategy is used to continue to execute the strategy evaluation and improvement steps until the strategy no longer changes in all states. After that, in each state, the operation strategy that maximizes the value function is selected and used as the new operation strategy for the FPSO riser support system. This can improve the intelligence and adaptability of the operation strategy, ensure that the riser support system is always in the optimal control state under different working conditions, achieve high efficiency of multi-objective optimization, and help find the best balance between reducing vibration, reducing wear and extending equipment life, thereby achieving a dual improvement in economy and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0048] Figure 1 This is a system block diagram of the real-time simulation platform for the FPSO riser support system based on Modelica proposed in the present invention. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Example 1

[0050] Reference Figure 1 The real-time simulation platform of the FPSO riser support system based on Modelica includes a requirement definition module, a data loading module, an environmental simulation module, a riser support modeling module, a system verification module, a simulation calculation module, an optimization scheduling module, an evaluation and analysis module, a control suggestion module, a real-time visualization module, a storage backtracking module and a feedback adjustment module.

[0051] The demand definition module is used for users to input operational requirements and convert the requirements into parsable tasks; the data loading module is used to load various basic data sets such as FPSO platform structural parameters, riser material properties, support system design standards and historical operation data; the environmental simulation module is used to simulate the environment through random ocean processes and generate simulation scenario inputs.

[0052] Specifically, the wave, wind speed and tidal current environmental factors in the marine environment are parameterized by the Pierson-Moskowitz spectrum to generate a wave spectrum model. The value range and probability distribution of each environmental factor are obtained based on the wave spectrum model. Each group of environmental factors is divided into multiple equal probability intervals, and the boundary points of each equal probability interval are set by the cumulative distribution function. Then, for each environmental factor, one environmental factor is randomly selected from each interval according to the divided multiple equal probability intervals, and the extraction is repeated until the preset numerical value is reached. The corresponding LHS matrix is ​​constructed according to the extracted groups of environmental factors. In the multiple intervals of each factor, the interval order is randomly arranged. Then, the distribution function of the environmental factor is used to map the standardized value in the LHS matrix to the actual physical space. After the mapping is completed, all environmental factors are integrated to generate the final environmental condition sample set. According to the evaluation indicators of the importance of the working condition, the economy and the probability of occurrence of the environmental condition, a weight evaluation indicator matrix is ​​constructed, and the weight of each group of evaluation indicators is calculated by the hierarchical analysis method. Based on the environmental condition samples and the weight matrix, the comprehensive score is calculated, and the multiple groups of samples with the highest scores are selected as the environmental condition combination to generate the simulation scenario input.

[0053] In this embodiment, the specific calculation formula of the Pierson-Moskowitz spectrum is as follows:

[0054] ;

[0055] In the formula, represents the wave energy spectral density; and Represent the empirical coefficients respectively; represents the acceleration due to gravity; Represents significant wave height.

[0056] The riser support modeling module is used to build a dynamic model of the riser support system based on Modelica.

[0057] Specifically, the riser support system is decomposed into multiple subsystems and components, and the physical characteristics and interactions of each subsystem are collected and set. Then, based on Newtonian mechanics and Lagrangian dynamics, the motion equations of the riser and support system are established, and a spring damping model is applied at the support point to describe the interaction between the riser and the support structure. Then, the physical models of each subsystem are deployed and implemented in the Modelica software, and the material properties, geometric parameters and boundary conditions of each subsystem model are input. The fluid-solid coupling model is used to simulate the force of the fluid on the structure. The riser, support structure and fluid-solid coupling model are integrated in the Modelica software, and the initial conditions and simulation parameters are configured, and the simulation step size and real-time calculation framework are configured.

[0058] The system verification module is used to verify the accuracy of the dynamic model based on historical data and experimental data, and to identify existing modeling errors and automatically correct them. Example 2

[0059] Reference Figure 1 The real-time simulation platform of the FPSO riser support system based on Modelica includes a requirement definition module, a data loading module, an environmental simulation module, a riser support modeling module, a system verification module, a simulation calculation module, an optimization scheduling module, an evaluation and analysis module, a control suggestion module, a real-time visualization module, a storage backtracking module and a feedback adjustment module.

[0060] The simulation calculation module is used to calculate the response of the dynamic model under actual environmental conditions; the optimization scheduling module is used to globally optimize the parameter configuration of the riser support system.

[0061] Specifically, maximizing the stability of the riser, minimizing the vibration amplitude and minimizing the cost of the support system are taken as optimization objectives, and the performance indicators of the riser support system are converted into objective functions. Objective function constraints are set based on the parameter range, and a group of population individuals are randomly generated, and each individual represents a set of parameter configurations of the riser support system. The comprehensive score of each individual in the population is obtained through the objective function, and the decision plan with the highest comprehensive score is taken as the optimal individual. A group of coefficient vectors are set, and a random number between 0 and 1 is generated in each round of iteration. If the generated random number is greater than the preset probability parameter, the coefficient and step size for controlling the position update are calculated according to the coefficient vector, and it is judged whether the remaining individuals are shrinking around the optimal solution according to the size of the direction. If the coefficient is less than 1, it means that the remaining individuals are surrounding the optimal individual, and the remaining individuals are positioned according to the optimal individual. The position is updated, that is, the parameter configuration of each individual is adjusted. If the coefficient is ≥1, it means that the remaining individuals are far away from the optimal individual. Through random search, random positions are selected in the population space, and the positions of the remaining individuals are updated. After each iteration, the coefficient vector is updated based on the linear decreasing rule. If the generated random number is less than or equal to the preset probability parameter, the distance between the positions of the remaining individuals in the population and the position of the optimal individual is calculated, and the spiral motion formula is used to simulate the movement law of each individual approaching the optimal individual along the spiral trajectory, update the individual position, repeatedly select the optimal individual and iteratively update the position until the comprehensive score change value converges to the preset threshold range, then compare the comprehensive scores of the individuals in each group, and output the individual with the highest comprehensive evaluation score as the optimal parameter configuration of the system, and adjust the simulation parameters of the current support system dynamic model based on the optimal parameter configuration.

[0062] It should be further explained that the specific calculation formula of the objective function is as follows:

[0063] ;

[0064] In the formula, Representative Parameter configuration of group individuals The fitness function value of Represents the total duration of the simulation; Representative time steps; Representative In time steps, based on parameter configuration The riser vibration response; Represents the target vibration value; A penalty term representing the cost.

[0065] The evaluation and analysis module is used to comprehensively evaluate performance and identify potential risks; the control recommendation module is used to analyze the impact of different operating strategies on system performance and generate optimal control recommendations.

[0066] Specifically, all states and operation strategies of the riser support system are collected, and the corresponding state space and action space are established. Then, the continuous state variables and operation strategies of the system in the state space and action space are discretized. Through simulation or statistical data, the probability of the system transferring from any state to the next state under the action of the operation strategy is calculated. A reward value is set for each state-operation strategy pair to obtain the impact of the operation strategy on the system performance. In the state space, a random operation strategy is assigned to each state to initialize the strategy. Through the Bellman equation, the value function of each state is updated according to the control instructions executed by the current strategy. The value function is gradually iterated and updated using a recursive calculation method until the change in the value function of all states is less than a preset threshold. The strategies before and after the update are compared. If the two are the same in all states, it is considered that the strategy has converged; otherwise, the new strategy is used to continue to execute the strategy evaluation and improvement steps until the strategy no longer changes in all states. Then, in each state, the operation strategy that maximizes the value function is selected as the new operation strategy of the FPSO riser support system.

[0067] The real-time visualization module is used to display the status changes of the FPSO riser support system in real time using 3D visualization technology; the storage and backtracking module is used to classify and store various data generated during the simulation process, and support rapid backtracking and re-analysis of the data; the feedback adjustment module is used to receive adjustment instructions from users or control systems, and dynamically adjust modeling parameters or optimization objectives.

Claims

1. A real-time simulation platform for FPSO riser support system based on Modelica, characterized in that: It includes demand definition module, data loading module, environmental simulation module, riser support modeling module, system verification module, simulation calculation module, optimization scheduling module, evaluation and analysis module, control suggestion module, real-time visualization module, storage backtracking module and feedback adjustment module; The requirement definition module is used for user input of operation requirements and converting the requirements into parseable tasks; The data loading module is used to load various basic data groups including FPSO platform structural parameters, riser material properties, support system design standards and historical operation data; The environment simulation module is used to simulate the environment through random ocean processes and generate simulation scenario input; The riser support modeling module is used to build a dynamic model of the riser support system based on Modelica; The system verification module is used to verify the accuracy of the dynamic model based on historical data and experimental data, and to identify existing modeling errors and automatically correct them; The simulation calculation module is used to calculate the response of the dynamic model under actual environmental conditions; The optimization scheduling module is used to globally optimize the parameter configuration of the riser support system; The evaluation and analysis module is used to comprehensively evaluate performance and identify potential risks; The control suggestion module is used to analyze the impact of different operation strategies on system performance and generate optimal control suggestions; The real-time visualization module is used to display the state changes of the FPSO riser support system in real time using 3D visualization technology; The storage backtracking module is used to classify and store various data generated during the simulation process, and supports fast backtracking and re-analysis of the data; The feedback adjustment module is used to receive adjustment instructions from the user or the control system, and dynamically adjust the modeling parameters or optimization objectives; The specific steps of generating the simulation scene input by the environment simulation module are as follows: S1.1: The wave, wind speed and tidal current environmental factors in the ocean environment are parameterized through the Pierson-Moskowitz spectrum to generate a wave spectrum model, and the value range and probability distribution of each environmental factor are obtained based on the wave spectrum model; S1.2: Divide each group of environmental factors into multiple equal probability intervals, and set the boundary points of each equal probability interval through the cumulative distribution function. Then, for each environmental factor, according to the multiple equal probability intervals, randomly select an environmental factor from each interval, and repeat the extraction until the preset value is reached; S1.3: Construct the corresponding LHS matrix based on the extracted groups of environmental factors. Randomly arrange the interval order in multiple intervals of each factor. Then use the distribution function of the environmental factor to map the standardized values ​​in the LHS matrix to the actual physical space. After the mapping is completed, integrate all environmental factors to generate the final environmental condition sample set. S1.4: Based on the evaluation indicators of the importance of working conditions, economy and probability of occurrence of environmental conditions, a weighted evaluation indicator matrix is ​​constructed, and the weight of each group of evaluation indicators is calculated using the hierarchical analysis method. Based on the environmental condition samples and the weight matrix, a comprehensive score is calculated, and multiple groups of samples with the highest scores are selected as the environmental condition combination to generate simulation scenario input.

2. The real-time simulation platform of the FPSO riser support system based on Modelica according to claim 1, characterized in that: The specific calculation formula of the Pierson-Moskowitz spectrum described in S1.1 is as follows: ； In the formula, represents the wave energy spectral density; and Represent the empirical coefficients respectively; represents the acceleration due to gravity; Represents significant wave height.

3. The real-time simulation platform of the FPSO riser support system based on Modelica according to claim 1, characterized in that: The specific steps of constructing the dynamic model of the riser support system by the riser support modeling module are as follows: S2.1: Decompose the riser support system into multiple subsystems and components, and collect and set the physical properties and interactions of each subsystem. Then, establish the equations of motion of the riser and support system based on Newtonian mechanics and Lagrangian dynamics; S2.2: Apply spring-damper models at the support points to describe the interaction between the riser and the support structure. Then deploy and implement the physical models of each subsystem in the Modelica software, input the material properties, geometric parameters and boundary conditions of each subsystem model, and use the fluid-structure interaction model to simulate the force of the fluid on the structure; S2.3: Integrate the riser, support structure, and fluid-structure interaction models in the Modelica software, configure the initial conditions and simulation parameters, and configure the simulation step size and real-time calculation framework.

4. The real-time simulation platform of the FPSO riser support system based on Modelica according to claim 3, characterized in that: The specific steps of global optimization of the optimization scheduling module are as follows: S3.1: Maximizing the stability of the riser, minimizing the vibration amplitude, and minimizing the cost of the support system are taken as optimization objectives, and the performance indicators of the riser support system are converted into objective functions. The objective function constraints are set based on the parameter range, and a group of population individuals are randomly generated, and each individual represents a set of parameter configurations of the riser support system; S3.2: Obtain the comprehensive score of each individual in the population through the objective function, take the decision plan with the highest comprehensive score as the optimal individual, set a set of coefficient vectors, and generate a random number between 0 and 1 in each round of iteration. If the generated random number is greater than the preset probability parameter, calculate the coefficient and step size of the control position update based on the coefficient vector, and judge whether the remaining individuals are shrinking around the optimal solution according to the size of the direction; S3.3: If the coefficient is less than 1, it means that the remaining individuals surround the optimal individual, and the positions of the remaining individuals are updated according to the optimal individual, that is, the parameter configuration of each individual is adjusted. If the coefficient is ≥ 1, it means that the remaining individuals are far away from the optimal individual. Through random search, random positions are selected in the population space, and the positions of the remaining individuals are updated. After each iteration, the coefficient vector is updated based on the linear decreasing rule. S3.4: If the generated random number is less than or equal to the preset probability parameter, the distance between the positions of the remaining individuals in the population and the position of the optimal individual is calculated, and the movement law of each individual along the spiral trajectory approaching the optimal individual is simulated through the spiral motion formula to update the individual position; S3.5: Repeat the optimal individual selection and iterative update of the position until the comprehensive score change value converges to the preset threshold range, then compare the comprehensive scores of individuals in each group, and output the individual with the highest comprehensive evaluation score as the optimal parameter configuration of the system, and adjust the simulation parameters of the current support system dynamic model based on the optimal parameter configuration.

5. The real-time simulation platform of the FPSO riser support system based on Modelica according to claim 4, characterized in that: The specific calculation formula of the objective function described in S3.1 is as follows: ； In the formula, Representative Parameter configuration of group individuals The fitness function value of Represents the total duration of the simulation; Representative time steps; Representative In time steps, based on parameter configuration The riser vibration response; Represents the target vibration value; A penalty term representing the cost.

6. The real-time simulation platform of the FPSO riser support system based on Modelica according to claim 4, characterized in that: The specific steps of the control suggestion module generating the optimal control suggestion are as follows: S4.1: Collect all states and operation strategies of the riser support system, and establish the corresponding state space and action space, then discretize the continuous state variables and operation strategies of the system in the state space and action space, and calculate the probability of the system transferring from any state to the next state under the action of the operation strategy through simulation or statistical data; S4.2: Set a reward value for each state-action strategy pair to obtain the impact of the action strategy on the system performance. In the state space, assign a random action strategy to each state to initialize the strategy. Update the value function of each state according to the control instructions executed by the current strategy through the Bellman equation. S4.4: Use a recursive calculation method to iteratively update the value function step by step until the change in the value function of all states is less than the preset threshold. Compare the strategies before and after the update. If the two are the same in all states, the strategy is considered to have converged; otherwise, use the new strategy to continue to perform the strategy evaluation and improvement steps until the strategy no longer changes in all states. Then, in each state, select the operating strategy that maximizes the value function and use it as the new operating strategy for the FPSO riser support system.

Images