Inertia optimization method for electric heating gas energy transport channel coordination

Abstract

The invention provides an inertia optimization method for electric heat gas energy transport channel coordination, and relates to the technical field of energy transport channels, and the method comprises the steps: building a fluid flow state and vortex intensity mapping relation model, which is used for predicting the possible vortex conditions under different working conditions; and based on a prediction result, a genetic algorithm is adopted to optimize a sensor arrangement scheme, and the most comprehensive flow state information is obtained by using the least sensors. According to the method, pipeline vibration safety is considered, a vibration monitoring and valve adjustment limiting mechanism is set, in addition, a tradeoff model of energy loss and transportation efficiency is further constructed, an optimal adjustment strategy is solved by applying a multi-objective optimization algorithm, finally, an eddy current suppression effect evaluation model is established, quantitative evaluation and strategy optimization of a control effect are achieved, and the control effect is optimized. Through the comprehensive application of a series of innovative methods, the precise inhibition of the vortex in the fluid transportation process and the remarkable improvement of the transportation efficiency are realized, and meanwhile, the safe operation of a pipeline system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an inertia optimization method for coordinating electric, thermal and gas energy transmission channels. Background Art

[0002] During the high-speed flow of the fluid in the electric heat gas energy transmission channel, due to the viscosity and inertia of the fluid, eddies are easily generated in the bends, valves, and diameter changes of the pipeline. The generation of eddies will increase the energy loss in the energy transmission process and reduce the transmission efficiency. At the same time, the presence of eddies will also aggravate the wear of the inner wall of the pipeline and shorten the service life of the pipeline. Eddies may also cause vibration and noise in the pipeline, posing a threat to the safe and stable operation of the pipeline.

[0003] In order to suppress the generation and development of eddies, it is necessary to arrange sensors in the pipeline to monitor the flow state of the fluid in real time, and dynamically adjust the valve opening or take other measures according to the monitoring data to change the flow characteristics of the fluid. However, how to choose the arrangement position and number of sensors to obtain sufficient flow state information without affecting normal transportation, and how to balance the relationship between the adjustment amplitude and the adjustment frequency to suppress eddies while minimizing interference with the transportation process, and how to adjust the adjustment strategy according to the changes in parameters such as the type, temperature, and pressure of the fluid to ensure the control effect. These are key technical issues that need to be solved urgently.

[0004] There is a contradiction between eddy current suppression and transport efficiency improvement. Although overly frequent or large-scale adjustments can effectively suppress eddy currents, they may change the transport parameters too much, resulting in a decrease in transport efficiency. How to find the best balance between eddy current suppression and efficiency improvement is a challenging optimization problem. In addition, active eddy current suppression may also introduce new energy consumption. How to choose appropriate control mechanisms and control strategies to achieve the best control effect at the lowest cost is also a problem worthy of in-depth study. Summary of the invention

[0005] The present invention provides inertia optimization for coordinated electric, thermal and gas energy transport channels, mainly including:

[0006] A mapping relationship model between fluid flow state and eddy intensity is established to predict possible eddy conditions under different working conditions. Based on the prediction results, a genetic algorithm is used to optimize the sensor layout scheme to obtain the most comprehensive flow state information with the least sensors. The optimized sensor layout scheme is used to collect real-time flow state data, and the valve adjustment strategy is optimized using a reinforcement learning algorithm to suppress eddy currents and improve transport efficiency. The strategy model is used to generate the optimal valve adjustment scheme in real time according to different fluid types, temperatures and pressure conditions. The pipeline vibration caused by valve adjustment is monitored in real time. When the vibration amplitude exceeds the preset threshold, the safety mechanism is triggered to limit the valve adjustment amplitude. An energy loss and transport efficiency trade-off model is constructed, and a multi-objective optimization algorithm is used to solve the model to obtain the optimal adjustment strategy that balances eddy current suppression and transport efficiency improvement. A eddy current suppression effect evaluation model is established to quantitatively evaluate the eddy current suppression effect. If the effect does not meet expectations, the secondary optimization of the adjustment strategy is initiated.

[0007] Furthermore, the establishment of a mapping relationship model between fluid flow state and eddy intensity includes: obtaining physical property data such as density, viscosity, and specific heat capacity of the fluid; performing numerical simulation using computational fluid dynamics software to obtain flow state data such as velocity distribution and pressure distribution of the flow field, as well as eddy characteristic data such as vorticity distribution and turbulence intensity; preprocessing the data and extracting key features as model input;

[0008] A support vector regression algorithm or a multi-layer perceptron neural network algorithm is used to train and establish a mapping relationship model between flow state and eddy current intensity.

[0009] Furthermore, the use of a genetic algorithm to optimize the sensor layout scheme includes: establishing a numerical simulation model of the pipeline flow state to obtain the flow state distribution information inside the pipeline; using a clustering algorithm to divide different flow state areas and determine key monitoring areas; constructing a code for the sensor layout scheme; designing a fitness function to comprehensively consider the number of sensors, measurement coverage quality, cost and vibration sensor layout; and using a genetic algorithm to iteratively search for the optimal layout scheme.

[0010] Furthermore, the application of reinforcement learning algorithm to optimize valve regulation strategy includes: constructing a simulation environment to simulate the fluid transport process; setting optimization goals and quantifying them as reward functions; using deep reinforcement learning algorithm to construct an intelligent agent model; the intelligent agent continuously interacts with the environment in the simulation environment to learn the optimal control strategy; deploying the optimal control strategy to the actual system and dynamically adjusting the valve opening according to real-time data.

[0011] Furthermore, the real-time monitoring of pipeline vibration caused by valve adjustment includes: obtaining vibration signals collected by vibration sensors; performing feature extraction on vibration data and calculating vibration amplitude; comparing the vibration amplitude with a preset threshold; if the vibration amplitude exceeds the threshold, triggering a safety protection mechanism to limit the valve adjustment amplitude, and reducing pipeline vibration by optimizing the valve adjustment strategy.

[0012] Furthermore, the construction of the energy loss and transport efficiency trade-off model includes: establishing a mathematical model for the trade-off optimization between eddy current suppression and transport efficiency; using a particle swarm optimization algorithm or a genetic algorithm to solve the model to obtain a Pareto frontier or a Pareto optimal solution set; and analyzing the optimization results to obtain an optimal adjustment strategy for balancing eddy current suppression and transport efficiency.

[0013] Furthermore, the establishment of an eddy current suppression effect evaluation model includes: obtaining eddy current related data collected by sensors; preprocessing the data; calculating the percentage of eddy current intensity reduction, the percentage of transport efficiency improvement and the percentage of energy loss reduction; weighted summing the three indicators to obtain a comprehensive evaluation score; if the score is lower than a preset threshold, triggering secondary optimization of the adjustment strategy, and using a particle swarm optimization algorithm to optimize the eddy current control parameters.

[0014] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0015] The present invention discloses an inertia optimization method for coordinating electric, hot and gas energy transport channels. The method first establishes a mapping model between fluid parameters and eddy strength, and uses a genetic algorithm to optimize the sensor layout scheme to achieve efficient information collection. Then, based on the collected real-time data, a reinforcement learning algorithm is applied to optimize the valve adjustment strategy, and a control scheme adapted to different working conditions is dynamically generated. In this process, the present invention takes pipeline vibration safety into consideration, and sets up vibration monitoring and valve adjustment restriction mechanisms. In addition, the present invention also constructs a trade-off model between energy loss and transport efficiency, and uses a multi-objective optimization algorithm to solve the optimal adjustment strategy. Finally, a eddy suppression effect evaluation model is established to achieve quantitative evaluation of the control effect and strategy optimization. Through the comprehensive application of this series of innovative methods, the present invention achieves precise suppression of eddies and significant improvement of transport efficiency during fluid transport, while ensuring the safe operation of the pipeline system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flow chart of an inertia optimization method for coordinating electric, thermal and gas energy transport channels. DETAILED DESCRIPTION

[0017] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0018] like Figure 1 In this embodiment, a method for optimizing the inertia of coordinated electric, thermal and gas energy transport channels may specifically include:

[0019] S101. A mapping relationship model between fluid flow state and vortex intensity is established based on fluid type, temperature and pressure parameters. The model uses machine learning algorithms, such as support vector regression or neural network, to input fluid parameters and output predicted vortex intensity. Model training data comes from experimental measurements and computational fluid dynamics simulations. The model is used to predict vortex conditions that may occur under different working conditions and provide decision-making basis for sensor layout and valve adjustment.

[0020] According to parameters such as fluid type, fluid temperature and fluid pressure, the physical property data such as density, viscosity and specific heat capacity of the fluid are obtained by consulting engineering manuals and material property tables. Computational fluid dynamics software such as ANSYS Fluent or OpenFOAM is used to perform numerical simulations on the target fluid under different working conditions to obtain flow state data such as velocity distribution and pressure distribution of the flow field, as well as vortex characteristic data such as vortex distribution and turbulence intensity. The obtained flow state and vortex characteristic data are preprocessed, including removing outliers, interpolating missing values, normalizing, etc., and extracting key features such as vortex mean and turbulence intensity mean as model input. The support vector regression algorithm is used, with flow state characteristics as input and vortex intensity mean as output, to train and establish a mapping relationship model between flow state and vortex intensity. Support vector regression can handle small samples and nonlinear problems well, and the model complexity is low. The prediction accuracy of the support vector regression model is evaluated on the test set. If the root mean square error is greater than the preset threshold, such as 5%, the multilayer perceptron neural network algorithm is used to retrain the model, and the network structure and hyperparameters are optimized to improve the prediction accuracy. The trained mapping relationship model is encapsulated as a standard Python function or RESTful interface, integrated into the monitoring system of the fluid equipment, receives the fluid parameters in real time and calls the model to predict the eddy current intensity. According to the predicted value of the eddy current intensity, combined with the performance parameters and applicable conditions of the eddy current suppression measures, the rule engine is used to automatically decide the sensor layout plan and valve adjustment strategy, and the execution instructions are sent to the field control system to achieve optimal control of fluid flow and reduce the adverse effects of eddy currents on equipment.

[0021] Specifically, fluid type, temperature and pressure are key parameters that determine the physical properties of fluids. For example,

[0022] For water, at a temperature of 20°C and a pressure of 1 standard atmosphere, the density is approximately 998 kg / m 3 , viscosity is about 0.02 mPa·s, and specific heat capacity is about 18 kJ / (kg·K). These data can be obtained by consulting the Handbook of Fluid Mechanics or online databases. The physical properties of different types of fluids vary greatly. For example, the density of air at the same temperature and pressure is about 2 kg / m 3, the viscosity is about 0.18 mPa·s. Obtaining accurate physical property data is the basis for fluid dynamics simulation. Computational fluid dynamics (CFD) software can be used to simulate the flow state of fluid under different working conditions. For example, to simulate the flow of water in a pipe, boundary conditions such as the geometry of the pipe, the inlet velocity of the water, and the outlet pressure can be set. By solving with software such as ANSYS Fluent or OpenFOAM, data such as the velocity distribution, pressure distribution, vorticity distribution, and turbulence intensity of the flow field can be obtained. For example, at the elbow of the pipe, the flow velocity may increase, the pressure may decrease, the vorticity will increase, and the turbulence intensity will also increase. These data intuitively show the flow state and vortex characteristics of the fluid. Before data analysis, the original data needs to be preprocessed. For example, there may be some outliers in the simulation results, which need to be removed. For missing data, interpolation methods can be used to complete them. In order to eliminate the influence of dimensions between different physical quantities, the data needs to be normalized, such as scaling the data to between 0 and 1. The preprocessed data can be used to establish a prediction model. For example, the mean of vorticity and the mean of turbulence intensity can be extracted as input features of the model. Support vector regression (SVR) is a commonly used machine learning algorithm that can be used to establish a mapping relationship between flow state and vortex intensity. For example, the mean of flow velocity, pressure and vortex is used as input, and the mean of turbulence intensity is used as output to train an SVR model. The SVR model can handle nonlinear relationships and has good generalization ability for small sample data. If the root mean square error of the model on the test set is greater than the preset threshold (for example, 5%), you can consider using the multi-layer perceptron (MLP) neural network algorithm to retrain the model and improve the prediction accuracy by adjusting the network structure and hyperparameters. The MLP neural network has stronger learning ability and can fit more complex nonlinear relationships. The trained model is encapsulated as a Python function or a RESTful interface, which can be easily integrated into the monitoring system of the fluid equipment. For example, the sensor collects the temperature, pressure and flow rate data of the fluid in real time, and the monitoring system inputs these data into the model to obtain the predicted value of the vortex intensity. According to the predicted value of vortex intensity, combined with the performance parameters and applicable conditions of vortex suppression measures, for example, installing a guide vane in the pipeline can reduce the intensity of the vortex. The rule engine can automatically determine the installation position and angle of the guide vane according to the predicted vortex intensity, or adjust the valve opening to control the flow rate, thereby reducing the adverse effects of vortex on the equipment, for example, vortex can cause pipeline vibration and energy loss. And send the execution instruction to the field control system, such as PLC, to achieve optimal control of fluid flow. For example, in the turbine inlet pipe, vortex can reduce the efficiency of the turbine and cause vibration. By predicting the vortex intensity, measures can be taken in advance, such as adjusting the angle of the guide vane, to reduce the impact of the vortex, thereby improving the efficiency of the turbine and extending its service life.Another example is in chemical pipelines, where eddies can cause localized corrosion and scaling. By predicting the eddy strength, the pipeline design can be optimized or fluid parameters, such as flow rate and temperature, can be adjusted to mitigate the effects of eddies, thereby improving pipeline safety and reliability.

[0023] S102. Based on the prediction results of the above model, a genetic algorithm is used to optimize the sensor layout scheme. A fitness function is constructed, which includes indicators such as the number of sensors, location, information acquisition quality and cost. The specific form of the fitness function is a weighted sum, and the weight of each indicator is determined by expert experience. The algorithm iteratively searches for the optimal layout scheme through crossover and mutation operations to obtain the most comprehensive flow state information with the least number of sensors. In this process, the layout of vibration sensors is also considered to monitor pipeline vibration.

[0024] According to the pipeline structure and fluid characteristic data, a numerical simulation model of pipeline flow state is established to obtain the flow state distribution information inside the pipeline. According to the simulated flow state distribution, the K-means clustering algorithm is used to divide different flow state areas and determine the key monitoring areas. According to the characteristics of each monitoring area, the type and number of pressure, flow, temperature and other sensors to be arranged are determined, and the encoding of the sensor layout scheme is constructed. The fitness function is designed, and the indicators such as the number of sensors, measurement coverage quality and cost are comprehensively considered. The advantages and disadvantages of the layout scheme are quantified in the form of weighted summation. The weight coefficient can be assigned according to the importance of the indicator. At the same time, according to the vibration characteristics of the pipeline, the evaluation index of the vibration sensor layout is introduced into the fitness function to balance the needs of flow monitoring and vibration monitoring. The genetic algorithm is used to optimize the sensor layout scheme, set the appropriate population size, crossover probability and mutation probability, and iterate the search for the optimal layout through selection, crossover and mutation operations. The convergence condition of the genetic algorithm is judged. If the change amplitude of the fitness value is less than a certain threshold for multiple consecutive iterations, the algorithm is considered to have converged, and the optimal sensor layout scheme at this time is output. The optimized sensor layout scheme is applied to the actual pipeline system, sensors are installed at corresponding positions, and data acquisition equipment is connected to realize online monitoring of pipeline flow status and vibration.

[0025] Specifically, the numerical simulation of the pipeline flow state is the basis of the sensor layout scheme. First, a geometric model needs to be established based on the CAD model of the pipeline, for example, a straight pipe with a diameter of 1 meter and a length of 10 meters. Then, the fluid characteristic parameters are set, for example, the density of water is 998 kilograms per cubic meter and the viscosity is 0.01 Pascal second. Then, the boundary conditions are set, for example, the inlet flow rate is 1 meter per second and the outlet pressure is 1 standard atmosphere. The model is solved using computational fluid dynamics (CFD) software, such as ANSYS Fluent, to obtain the velocity field, pressure field and temperature field distribution inside the pipeline. The simulation results show that the flow velocity in the central area of ​​the pipeline is higher, and the flow velocity near the wall area is lower, showing an obvious boundary layer effect. After obtaining detailed flow state distribution information inside the pipeline, the K-means clustering algorithm can be used to divide the flow state into regions. For example, according to parameters such as flow velocity, pressure and temperature, the flow state in the pipeline is divided into three regions: high-speed zone, transition zone and low-speed zone. The division results can be intuitively displayed on the visualization interface of the simulation results, and different colors represent different flow state regions. The high-speed area is mainly concentrated in the center of the pipeline, while the low-speed area is close to the pipe wall. This division method can help determine the areas that need to be monitored. For example, at the junction of the high-speed area and the transition area, the state of the fluid changes dramatically, and unstable phenomena such as eddy currents are prone to occur, which requires special attention. After determining the key monitoring areas, it is necessary to select the appropriate sensor type and quantity according to the characteristics of each area. For example, in the high-speed area, an electromagnetic flowmeter can be selected to measure the flow rate, a pressure sensor can be selected to measure the pressure, and a thermocouple can be selected to measure the temperature. In the transition area, due to the drastic changes in the flow state, the number of sensors can be increased and sensors with faster response speed can be selected. In the low-speed area, the number of sensors can be appropriately reduced. The layout of the sensor can be represented by a code. For example, 10110 means that pressure, temperature, flow, temperature and pressure sensors are arranged at five monitoring points respectively. In order to evaluate the advantages and disadvantages of the sensor layout plan, a fitness function needs to be designed. This function comprehensively considers indicators such as the number of sensors, measurement coverage quality and cost. For example, the fitness function can be defined as: fitness = 5*coverage-3*cost-2*quantity. Among them, coverage indicates the proportion of the sensor measurement range to the entire pipeline area, cost indicates the cost of the sensor and its installation and maintenance, and quantity indicates the total number of sensors. The weight coefficient reflects the importance of each indicator and can be adjusted according to actual needs. For example, if more attention is paid to the measurement coverage quality, the weight coefficient of coverage can be increased. Pipeline vibration is also an important monitoring indicator. Therefore, it is necessary to introduce evaluation indicators for the layout of vibration sensors in the fitness function. For example, the location and number of vibration sensors can be determined based on the modal analysis results of pipeline vibration, and the coverage of vibration measurement can be used as part of the fitness function. This can balance the needs of flow monitoring and vibration monitoring.Genetic algorithm is a commonly used optimization algorithm that can be used to find the optimal sensor layout scheme. First, it is necessary to set the appropriate population size, crossover probability and mutation probability. For example, the population size is set to 50, the crossover probability is set to 8, and the mutation probability is set to 1. Then, through operations such as selection, crossover and mutation, the optimal solution is continuously iterated. For example, the selection operation can retain individuals with higher fitness values, the crossover operation can combine the codes of two individuals, and the mutation operation can randomly change certain bits in the individual code. When the fitness value change amplitude is less than a certain threshold value for multiple consecutive iterations, such as 01, the algorithm is considered to have converged and the optimal sensor layout scheme at this time is output. Finally, the optimized sensor layout scheme is applied to the actual pipeline system. For example, pressure sensors, flow sensors, temperature sensors and vibration sensors are installed on the pipeline according to the scheme. These sensors are connected to the data acquisition equipment and transmit the data to the monitoring center to realize the online monitoring of the flow state and vibration of the pipeline. Through real-time monitoring data, abnormal conditions in the pipeline, such as eddy currents, leakage and vibration exceeding the standard, can be discovered in time, and corresponding measures can be taken to ensure the safe operation of the pipeline.

[0026] S103. Collect real-time flow state data using the optimized sensor layout. Combine these data and apply the reinforcement learning algorithm to optimize the valve adjustment strategy. Construct a simulation environment to simulate the fluid transport process, with the optimization goals of suppressing vortex and improving transport efficiency. The reinforcement learning agent learns the optimal control strategy by continuously trying different valve opening adjustment schemes in the simulation environment.

[0027] According to the geometric structure of the pipeline, fluid properties and other parameters, a three-dimensional simulation model of the fluid transport process is constructed using computational fluid dynamics software such as ANSYS Fluent. The standardized flow state data set is imported into the simulation model for boundary condition setting and initialization. The optimization objectives are set in the simulation environment, including minimizing the pressure loss in the pipeline and maximizing the fluid transport efficiency, and are quantified into numerical reward functions as the optimization basis of the reinforcement learning algorithm. A deep reinforcement learning algorithm, such as the Deep Deterministic Policy Gradient (DDPG) algorithm, is used to construct an intelligent agent model, with flow state data as input and valve opening adjustment strategy as output. In the simulation environment, the intelligent agent continuously interacts with the environment, obtains reward feedback based on the optimization objective, uses the neural network approximation function and the policy function, updates the model parameters through the gradient descent algorithm, and gradually learns the optimal control strategy. The optimal control strategy obtained by training is deployed in the control module of the actual fluid transport system, and the valve opening is dynamically adjusted using the trained intelligent agent model based on the real-time collected flow state data. In the actual application process, the operating status and performance indicators of the system, such as pipeline pressure, flow rate, transportation efficiency, etc., are continuously monitored and compared with the baseline values ​​before optimization to evaluate the optimization effect. At the same time, the operating data of the actual system is regularly transmitted back to the simulation environment to retrain and optimize the intelligent model, so as to achieve continuous iterative updates of the strategy and adapt to changes in actual working conditions. In order to further improve the optimization effect and system robustness, it is possible to consider introducing an online learning mechanism, that is, during the operation of the actual system, the intelligent model is fine-tuned and updated according to the real-time collected data, so that it can dynamically adapt to changes in working conditions and external disturbances. In addition, safety thresholds and constraints, such as pipeline pressure upper limit and flow rate range, can be set to ensure that the execution of the optimization strategy will not affect the safe and stable operation of the system.

[0028] Specifically, the pipe geometry and fluid properties are the basis for building a simulation model. For example, we can imagine a straight pipe with a length of 10 meters and a diameter of 5 meters. The transport medium is water at room temperature, the density of water is 998 kg per cubic meter, and the viscosity is 0.01 Pas. These parameters will be used to build a three-dimensional pipe model in CFD software such as ANSYS Fluent and define the physical properties of the fluid. Standardized flow state data sets are used to set boundary conditions and initialize simulations. For example, the inlet boundary condition can be set to a velocity inlet, and the velocity value comes from the data set; the outlet boundary condition can be set to a pressure outlet, and the pressure value also comes from the data set. The initial condition can be set to a stationary fluid in the pipe, and its temperature, pressure and other parameters come from the data set. This can make the simulation closer to the actual working conditions. The optimization target needs to be quantified into a numerical reward function. Taking minimizing pressure loss as an example, the pressure difference between the inlet and outlet of the pipe can be used as the negative value of the reward function. The smaller the pressure difference, the higher the reward value. Taking maximizing fluid transport efficiency as an example, the mass or volume of fluid passing through the pipe per unit time can be used as the positive value of the reward function. The larger the transport volume, the higher the reward value. The DDPG algorithm is a deep reinforcement learning algorithm that is suitable for control problems in continuous action space, such as the adjustment of valve opening. The input of the agent model can be sensor data such as pressure and flow rate at multiple locations in the pipeline, and the output is the valve opening value, which changes continuously between 0 and 1. The interaction process between the agent and the simulation environment is as follows: the agent outputs the valve opening control strategy based on the current flow state data; the simulation environment calculates the new flow state based on the valve opening, and feeds back the new state and reward value to the agent; the agent updates the neural network parameters based on the reward value and learns a better control strategy. The trained control strategy can be deployed in the actual system. For example, the trained neural network model can be embedded in the control system to collect data such as pressure and flow rate in the pipeline in real time, and calculate the optimal valve opening based on these data. The feedback of the actual system operation data can be used for model retraining and optimization. For example, at regular intervals, the flow state data and corresponding control strategy collected by the actual system are uploaded to the server to update the agent model. This allows the model to adapt to changes in actual working conditions and improve control performance. The online learning mechanism can further improve the optimization effect and system robustness. For example, incremental learning methods can be used to fine-tune the intelligent model based on real-time data during the actual system operation, so that it can quickly adapt to changes in operating conditions and external disturbances. The setting of safety thresholds and constraints can ensure the safe and stable operation of the system. For example, an upper limit for pipeline pressure can be set. If the valve opening calculated by the control strategy causes the pipeline pressure to exceed the upper limit, the opening is limited to ensure pipeline safety. Similarly, the range of flow rate can be set to prevent the system from malfunctioning due to excessively high or low flow rates.

[0029] S104. Based on the strategy model obtained through reinforcement learning training, the valve adjustment strategy is dynamically generated for different fluid types, temperature and pressure conditions. In the actual transportation process, the strategy model is used to generate the optimal adjustment plan in real time according to the current working condition data collected by the sensor, so as to realize the adaptive adjustment of the control strategy and improve the accuracy and real-time performance of vortex suppression.

[0030] According to the historical operating condition data of the transportation pipeline, a deep reinforcement learning algorithm, such as DQN or DDPG, is used to train the valve adjustment strategy model to obtain the initial strategy model. The input of the model is the state data of the temperature and pressure of the fluid in the pipeline, and the output is the valve opening adjustment value. In the actual transportation process, the state data of the fluid is collected in real time through the temperature sensor and pressure sensor installed in the pipeline. The collected real-time state data is input into the trained strategy model, and the optimal valve opening adjustment value under the current state is obtained through forward propagation calculation. According to the valve opening adjustment value generated by the strategy model, the valve actuator is controlled to adjust the valve in real time to change the valve opening, thereby adjusting the flow rate of the fluid in the pipeline to achieve the purpose of suppressing vortex. Before and after the valve adjustment, the state parameters of the fluid in the pipeline, such as temperature and pressure, are recorded respectively. The state parameters before and after the adjustment are compared and analyzed, and the suppression effect of the valve adjustment strategy on the vortex is judged according to the preset vortex evaluation indicators, such as temperature standard deviation and pressure pulsation frequency. According to the suppression effect, the valve adjustment strategy is scored as the reward value of reinforcement learning. The new state data and score reward value after valve adjustment are input into the reinforcement learning algorithm, and the parameters of the strategy model are updated and optimized through optimization methods such as gradient descent, so that it can adapt to changes in actual transportation conditions. Repeat the above process of data collection, strategy generation, valve adjustment, effect evaluation and model update, so that the valve adjustment strategy model can be adaptively adjusted according to the real-time working condition changes of the transportation pipeline, continuously improve the accuracy and real-time performance of vortex suppression, and ensure the safe and stable operation of the transportation pipeline.

[0031] Specifically, deep reinforcement learning can be used to optimize the valve adjustment strategy of the transportation pipeline, suppress vortex and improve transportation efficiency. Deep reinforcement learning algorithms represented by DQN and DDPG can handle complex continuous action spaces, such as the adjustment of valve opening. First, it is necessary to train an initial policy model using historical operating data. Suppose there is a long-distance pipeline that transports crude oil. The historical data contains the crude oil temperature, pressure and corresponding optimal valve opening in the pipeline under different operating conditions. These data can be used to train a neural network model. The input of the model is the crude oil temperature and pressure, and the output is the valve opening. For example, when the crude oil temperature is 50 degrees Celsius and the pressure is 5 MPa, the valve opening output by the model is 7. This initial model provides a starting point for the subsequent reinforcement learning process. Next, in the actual transportation process, it is necessary to collect the state data of the fluid in the pipeline in real time. Suppose distributed temperature sensors and pressure sensors are installed on the pipeline, which can monitor the crude oil temperature and pressure at different locations in the pipeline in real time. For example, the sensor collects data once a second and transmits the data to the control system. The collected real-time data will be input into the trained policy model. For example, the current collected crude oil temperature is 60 degrees Celsius and the pressure is 6 MPa. These two values ​​are input into the strategy model, and the model will output a valve opening, such as 8. The control system controls the valve actuator to adjust the valve in real time according to the valve opening value output by the strategy model. For example, the control system sends a command to the valve actuator to adjust the valve opening to 8. Before and after the valve adjustment, the state parameters of the fluid in the pipeline are recorded respectively. For example, before the adjustment, the crude oil temperature is 60 degrees Celsius and the pressure is 6 MPa. After the adjustment, the crude oil temperature becomes 58 degrees Celsius and the pressure becomes 5 MPa. By comparing the state parameters before and after the adjustment, the effect of the valve adjustment strategy on the suppression of vortex can be evaluated. The vortex evaluation indicators, such as the temperature standard deviation and the pressure pulsation frequency, are pre-set. Assume that the temperature standard deviation is 2 degrees Celsius and the pressure pulsation frequency is 10 Hz before the adjustment, and the temperature standard deviation is 1 degree Celsius and the pressure pulsation frequency is 5 Hz after the adjustment. This shows that the valve adjustment strategy effectively suppresses the vortex. According to the suppression effect, the valve adjustment strategy is scored as the reward value of reinforcement learning. For example, if the vortex suppression effect is good, a positive reward such as +1 is given; if the vortex suppression effect is poor, a negative reward such as -1 is given. In this case, since the vortex is effectively suppressed, a reward of +1 is given. The new state data and the score reward value after valve adjustment are input into the reinforcement learning algorithm to update and optimize the parameters of the strategy model. For example, the parameters of the neural network model are updated using the gradient descent algorithm so that the model can better adapt to changes in actual working conditions. Repeat the above process of data collection, strategy generation, valve adjustment, effect evaluation and model update. The strategy model will continue to learn and improve, and will eventually be able to make adaptive adjustments based on the real-time working conditions of the transport pipeline, thereby improving the accuracy and real-time performance of vortex suppression.This can improve transportation efficiency, reduce energy consumption, and ensure the safe and smooth operation of the transportation pipeline. Deep reinforcement learning is used because it can handle complex nonlinear relationships and can autonomously learn optimal control strategies without the need for pre-set rules.

[0032] S105. Real-time monitoring of pipeline vibration caused by valve adjustment. When the vibration amplitude exceeds the preset threshold, the safety mechanism is triggered to limit the valve adjustment amplitude to avoid pipeline safety problems caused by overly aggressive adjustment.

[0033] The pipeline vibration data caused by valve adjustment is obtained, and the time domain vibration signal collected by the vibration sensor is Fourier transformed to obtain the frequency domain vibration data. The frequency domain vibration data is feature extracted, and the characteristic values ​​such as vibration frequency and amplitude are calculated to obtain the pipeline vibration amplitude value. The pipeline vibration amplitude value is compared with the preset vibration amplitude threshold in real time to determine whether the current pipeline vibration amplitude exceeds the preset threshold. If the pipeline vibration amplitude exceeds the preset threshold, the safety protection mechanism is triggered. The safety protection mechanism includes: according to the degree of exceeding the threshold, the limit coefficient of the valve adjustment amplitude is calculated, and the limit coefficient is proportional to the degree of exceeding the threshold. The limit coefficient is multiplied by the current adjustment amplitude of the valve to obtain the limited valve adjustment amplitude, which is used as the upper limit value of the valve adjustment. In the case of limited valve adjustment, the pipeline vibration is reduced by optimizing the valve adjustment strategy. The specific method is: the valve adjustment signal is low-pass filtered to filter out the high-frequency adjustment component and obtain a gentle adjustment signal curve. The valve control instruction is generated according to the gentle adjustment curve, so that the valve is slowly adjusted according to the gentle adjustment curve to avoid the sudden increase of pipeline vibration caused by the rapid opening and closing of the valve. Continuously monitor the pipeline vibration. When the pipeline vibration amplitude is lower than the preset threshold for multiple times in a row, gradually relax the restriction on the valve adjustment amplitude according to a fixed step size until the restriction is completely lifted. Obtain valve control parameters such as valve opening and adjustment speed, and use them as sample data together with the pipeline vibration data at the corresponding time. Use the support vector machine (SVM) algorithm to train the sample data and establish a nonlinear association model between valve control parameters and pipeline vibration. Use the trained SVM model to predict the pipeline vibration under different valve control parameter combinations based on the current pipeline vibration state. Select the valve control parameter combination with the smallest predicted vibration amplitude as the current optimal control strategy, and generate valve control instructions based on this control strategy. At the same time, use the SVM model to predict the pipeline vibration trend and dynamically adjust the vibration amplitude threshold so that the threshold setting is adapted to the current pipeline operating conditions.

[0034] Specifically, pipeline vibration is an important safety indicator in the operation of transportation pipelines. Excessive vibration may cause pipeline fatigue or even rupture. In order to ensure pipeline safety, it is necessary to monitor and control pipeline vibration caused by valve adjustment in real time. First, install a vibration sensor on the pipeline to collect pipeline vibration signals. For example, an acceleration sensor is installed on the pipeline near the valve to measure the vibration acceleration of the pipeline in real time. The signal collected by the sensor is a time domain signal, which reflects the change of pipeline vibration over time. In order to analyze the frequency component of the vibration signal, the time domain signal needs to be converted into a frequency domain signal. Fast Fourier transform (FFT) can be used to convert the time domain vibration signal into frequency domain vibration data. Frequency domain data can display vibration components of different frequencies and their amplitudes. Feature extraction is performed on the frequency domain vibration data, such as calculating the main frequency of vibration and the corresponding amplitude. Assume that after Fourier transform, it is found that the main frequency component of pipeline vibration is 50 Hz, and the corresponding amplitude is 5 mm. This 5 mm amplitude value is the pipeline vibration amplitude value of interest. The extracted vibration amplitude value is compared with the preset vibration amplitude threshold. The preset threshold is determined based on factors such as pipeline material and operating pressure. For example, assume that according to pipeline safety regulations, the vibration amplitude threshold of the pipeline is set to 8 mm. Since the current vibration amplitude of 5 mm is less than the threshold of 8 mm, the pipeline vibration is within the safe range. If the pipeline vibration amplitude exceeds the preset threshold, the safety protection mechanism is triggered. Assume that at a certain moment, due to the rapid opening of the valve, the pipeline vibration amplitude reaches 2 mm, exceeding the preset threshold of 8 mm. At this time, the safety protection mechanism is triggered. The safety protection mechanism first calculates the limit coefficient of the valve adjustment amplitude. The limit coefficient is proportional to the degree of exceeding the threshold. For example, assume that the vibration amplitude exceeds the threshold by 50% ((2-8) / 8=5), then the limit coefficient is set to 5. Multiply the limit coefficient by the current adjustment amplitude of the valve to obtain the limited valve adjustment amplitude. Assuming that the current adjustment amplitude of the valve is 10%, the limited adjustment amplitude is 5*10%=5%. In other words, the valve opening adjustment cannot exceed 5%. In the case of limited valve adjustment, the valve adjustment strategy needs to be optimized to reduce pipeline vibration. The valve adjustment signal can be low-pass filtered to filter out the high-frequency adjustment component. This is equivalent to smoothing the valve adjustment to avoid rapid valve switching. For example, the valve control signal can be passed through a low-pass filter with a cutoff frequency of 1 Hz, which can filter out control signals with a frequency higher than 1 Hz, making the valve adjustment smoother. Continuously monitor the pipeline vibration. When the pipeline vibration amplitude is lower than the preset threshold for multiple consecutive times, gradually relax the limit on the valve adjustment amplitude. For example, if the vibration amplitude is lower than 8 mm for 5 consecutive times, reduce the restriction coefficient from 5 to 4, and so on, until the restriction is completely lifted. In order to establish a correlation model between valve control parameters and pipeline vibration, sample data needs to be collected. The sample data includes valve control parameters such as valve opening and adjustment speed, as well as pipeline vibration data at the corresponding time.For example, the pipeline vibration amplitude is 6 mm when the valve opening is 50% and the adjustment speed is 2% / second. The collected sample data is used to train the support vector machine (SVM) model. The SVM model can learn the nonlinear relationship between valve control parameters and pipeline vibration. Using the trained SVM model, the pipeline vibration under different valve control parameter combinations can be predicted. For example, the pipeline vibration amplitude can be predicted when the valve opening is 60% and the adjustment speed is 1% / second. The valve control parameter combination with the smallest predicted vibration amplitude is selected as the current optimal control strategy. For example, if it is predicted that the vibration amplitude is the smallest when the valve opening is 55% and the adjustment speed is 5% / second, this parameter combination is used as the current optimal control strategy and the corresponding valve control instructions are generated. At the same time, the SVM model can also predict the pipeline vibration trend and dynamically adjust the vibration amplitude threshold according to the prediction results. For example, if it is predicted that the pipeline vibration trend is rising, the vibration amplitude threshold can be appropriately increased to take preventive measures in advance.

[0035] S106. Construct a trade-off model between energy loss and transport efficiency. The model takes into account factors such as the degree of vortex suppression, fluid transport rate, and energy consumption. A multi-objective optimization algorithm, such as NSGA-II (non-dominated sorting genetic algorithm II), is used to solve the model. The algorithm sets parameters such as population size, crossover rate, and mutation rate, and iteratively searches for the Pareto optimal solution set to obtain the optimal adjustment strategy that balances vortex suppression and transport efficiency improvement.

[0036] According to the properties of energy loss and transport efficiency, a mathematical model for the trade-off optimization between eddy current suppression and transport efficiency is established. The eddy current suppression factor and transport efficiency factor are set as optimization targets in the model, and a mathematical relationship between the two is established. The multi-objective optimization model is converted into a standard form so that it can be solved by the optimization algorithm. The particle swarm optimization algorithm is used to solve the model. The population size is set to 50, the learning factors c1 and c2 are 0 respectively, the inertia weight w is 8, and the maximum number of iterations is 200. Initialize the particle position and velocity, update the particle position according to the fitness function, and obtain the Pareto frontier. The genetic algorithm is used to solve the model. The population size is set to 50, the crossover probability is 8, the mutation probability is 1, and the maximum evolutionary generation is 200. The population is selected, crossover and mutated, and the population is evolved according to the fitness function to obtain the Pareto optimal solution set. The optimized Pareto solution set is analyzed. According to the eddy current suppression factor, the eddy current suppression degree of the solution set is fuzzy comprehensively evaluated by the membership function method to obtain the fuzzy comprehensive evaluation value. According to the transport efficiency factor, the nine-scale method is used to construct the judgment matrix, and the sum-product method is used to calculate the weight vector to obtain the weighted score of the transport efficiency. The fuzzy comprehensive evaluation value and the weighted score are weighted and summed, and the weights can be adjusted according to actual needs. The solution with the highest final score is the optimal adjustment strategy that balances eddy current suppression and transport efficiency under the current weight. According to the eddy current suppression factor and transport efficiency factor values ​​corresponding to the strategy, the parameters of the actual system are adjusted to achieve the optimization effect.

[0037] Specifically, during pipeline transportation, energy loss will occur due to the viscosity of the fluid itself and the friction of the pipeline wall, among which eddy current is one of the main causes of energy loss. At the same time, transportation efficiency is also an important indicator of the pipeline transportation system. Therefore, it is necessary to balance and optimize eddy current suppression and transportation efficiency to achieve the best transportation effect. The generation of eddy current is related to the flow rate of the fluid and the geometric shape of the pipeline. For example, when the fluid flows through the location with large local resistance such as the pipeline elbow and valve, eddy current is easily generated. The intensity of the eddy current can be expressed by the eddy current suppression factor, which can be defined as the ratio of the average velocity of the eddy current area to the average velocity of the center line of the pipeline. The smaller the value of the eddy current suppression factor, the better the eddy current suppression effect. The transportation efficiency can be expressed by the transportation efficiency factor, which can be defined as the product of the volume of fluid transported per unit time and the cross-sectional area of ​​the pipeline. The larger the value of the transportation efficiency factor, the higher the transportation efficiency. There is a certain contradictory relationship between eddy current suppression and transportation efficiency. For example, in order to suppress eddy current, the flow rate can be reduced, but this will lead to a decrease in transportation efficiency. In order to improve the transport efficiency, the flow rate can be increased, but this will lead to the enhancement of vortex. Therefore, it is necessary to establish a mathematical model to describe the relationship between the vortex suppression factor and the transport efficiency factor and find an optimal balance point. The mathematical model can be expressed as a multi-objective optimization problem, the goal of which is to minimize the vortex suppression factor and maximize the transport efficiency factor at the same time. In order to simplify the model, it can be assumed that there is a linear relationship between the vortex suppression factor and the transport efficiency factor, for example, the vortex suppression factor increases linearly with the increase of the transport efficiency factor. In order to solve this multi-objective optimization problem, a particle swarm optimization algorithm can be used. Assume that the population size is 50, that is, there are 50 particles, each particle represents a possible solution. The position of each particle represents a set of values ​​of the vortex suppression factor and the transport efficiency factor. The particles update their positions based on their own experience and the best experience of the group to find a better solution. Genetic algorithms can also be used to solve this multi-objective optimization problem. Genetic algorithms simulate the evolutionary process in nature and continuously optimize the population through operations such as selection, crossover and mutation. Each individual in the population represents a possible solution. The fitness function is used to evaluate the pros and cons of each individual. A set of Pareto optimal solutions can be obtained through particle swarm optimization algorithm or genetic algorithm. Pareto optimal solution refers to the solution set in which any objective function value cannot be further improved without reducing the values ​​of other objective functions. In order to select the best solution from the Pareto optimal solution set, it is necessary to weigh eddy suppression and transport efficiency according to actual needs. For example, if more emphasis is placed on eddy suppression, a solution with a smaller eddy suppression factor can be selected; if more emphasis is placed on transport efficiency, a solution with a larger transport efficiency factor can be selected. In order to evaluate the degree of eddy suppression, the membership function method can be used. The membership function maps the eddy suppression factor to a value between 0 and 1, indicating the degree of eddy suppression.For example, the smaller the eddy current suppression factor, the larger the membership function value, indicating that the eddy current suppression effect is better. In order to evaluate the transport efficiency, the nine-scale method can be used to construct a judgment matrix. The judgment matrix represents the relative importance of different transport efficiency factors. Then, the weight vector is calculated by the sum-product method to obtain the weighted score of the transport efficiency. Finally, the fuzzy comprehensive evaluation value of eddy current suppression and the weighted score of transport efficiency are weighted and summed to obtain the final score. The solution with the highest score is the optimal adjustment strategy for balancing eddy current suppression and transport efficiency under the current weight. For example, assume that the eddy current suppression factor of a Pareto optimal solution is 2 and the transport efficiency factor is 8. The fuzzy comprehensive evaluation value of eddy current suppression calculated by the membership function is 9. The weighted score of transport efficiency calculated by the nine-scale method and the product method is 7. Assume that the weights of eddy current suppression and transport efficiency are 6 and 4, respectively. Then the final score of the solution is 6*9+4*7=82. According to the eddy suppression factor and transport efficiency factor values ​​corresponding to the optimal adjustment strategy, the parameters of the actual system can be adjusted. For example, the pipe cross-sectional area, fluid flow rate, pipe geometry and other parameters can be adjusted to achieve the optimization effect. Assume that the eddy suppression factor corresponding to the optimal adjustment strategy is 1 and the transport efficiency factor is 9. Then the pipe cross-sectional area can be appropriately reduced to reduce the eddy intensity, and the fluid flow rate can be appropriately increased to improve the transport efficiency.

[0038] S107. Establish a vortex suppression effect evaluation model to compare and analyze the changes in fluid flow state before and after adjustment. Based on sensor data, the model calculates indicators such as the percentage reduction of vortex intensity, the degree of improvement in transport efficiency, and energy loss. Quantitatively evaluate the vortex suppression effect. If the effect does not meet expectations, start the secondary optimization of the adjustment strategy to further improve the control effect.

[0039] The eddy current related data collected by the sensor, including parameters such as flow rate, pressure, and temperature, are obtained, and the acquired data are stored and constructed into an eddy current data set. The eddy current data set is preprocessed, and the moving average filtering method is used to remove outliers and noise, and the maximum and minimum normalization method is used to normalize the data to improve the data quality. According to the data subsets before and after the implementation of the eddy current suppression measures, the average eddy current velocity before and after the implementation is calculated, and the percentage of eddy current velocity reduction is obtained as a quantitative indicator of eddy current suppression intensity. By analyzing the changes in the flow rate, pipeline pressure difference and other parameters related to transportation efficiency before and after eddy current suppression, the percentage of transportation efficiency improvement is calculated as a quantitative indicator of transportation efficiency. The kinetic energy loss and thermal energy loss of the fluid before and after eddy current suppression are calculated to obtain the percentage of energy loss reduction as a quantitative indicator of energy loss. The weight coefficients of the percentage of eddy current intensity reduction, the percentage of transportation efficiency improvement and the percentage of energy loss reduction are set to 4, 3 and 3 respectively, and the three indicators are weighted and summed according to the weights to obtain the comprehensive evaluation score of the eddy current suppression effect. If the comprehensive evaluation score is lower than the preset threshold (such as 80 points), the secondary optimization of the adjustment strategy is triggered. The particle swarm optimization algorithm is used to improve the comprehensive evaluation score as the optimization goal. The vortex control parameters, such as the inclination angle of the swirl plate and the spacing of the suppression device, are optimized through iterative search. After multiple rounds of iterations, the optimal parameter combination that makes the comprehensive evaluation score reach the expected target is obtained.

[0040] Specifically, the sensor can collect parameters such as flow rate, pressure and temperature of the fluid in the pipeline to construct an eddy current data set. For example, a series of sensors are arranged in the pipeline, which can be ultrasonic flow meters, pressure sensors and temperature sensors, etc., to monitor the state of the fluid in real time. The data of these sensors can be transmitted to the data acquisition system for storage and preprocessing to form an eddy current data set. In order to improve the data quality, the collected eddy current data set needs to be preprocessed. For example, the moving average filtering method can be used to remove outliers and noise in the data. Assuming that there are some spikes in the collected flow rate data, it may be caused by the instantaneous error of the sensor, which can be smoothed out by moving average filtering. In addition, the maximum and minimum normalization method can be used to normalize the data, scale the data range to between 0 and 1, avoid the influence of data of different dimensions, and facilitate subsequent analysis and modeling. In order to evaluate the effect of eddy current suppression, it is necessary to calculate the quantitative index of eddy current suppression intensity. For example, data is collected for a period of time before and after the implementation of eddy current suppression measures, and the average eddy current velocity is calculated. Assuming that the average eddy velocity before implementation is 1 meter per second and the average eddy velocity after implementation is 0.5 meters per second, the percentage of eddy velocity reduction is 50%, indicating that the eddy suppression effect is more significant. In addition to the eddy suppression intensity, it is also necessary to evaluate the change in transport efficiency. Transport efficiency can be measured by parameters such as flow rate and pipeline pressure difference. For example, assuming that after the implementation of eddy suppression measures, the flow rate increased by 10%, while the pipeline pressure difference decreased by 5%, the percentage of transport efficiency improvement can be comprehensively calculated by the changes in these two parameters. Energy loss is also an important evaluation indicator. Eddy suppression measures can reduce fluid kinetic energy loss and thermal energy loss. For example, assuming that after the implementation of eddy suppression measures, the fluid kinetic energy loss decreased by 8% and the thermal energy loss decreased by 3%, the percentage of energy loss reduction can be comprehensively calculated by the changes in these two parameters. In order to comprehensively evaluate the eddy suppression effect, the percentage of eddy intensity reduction, the percentage of transport efficiency improvement, and the percentage of energy loss reduction can be weighted and summed. For example, if the weight coefficients of the three indicators are set to 4, 3, and 3 respectively, the comprehensive evaluation score of the eddy suppression effect can be calculated. Assuming that the eddy current intensity is reduced by 50%, the transport efficiency is improved by 10%, and the energy loss is reduced by 5%, the comprehensive evaluation score is 4×50%+3×10%+3×5%=245 points. If the comprehensive evaluation score is lower than the preset threshold, such as 80 points, the adjustment strategy needs to be optimized twice. For example, a particle swarm optimization algorithm is used to search for the optimal eddy current control parameters with the goal of improving the comprehensive evaluation score. These parameters may include the inclination angle of the swirl plate, the spacing of the suppression device, and so on. Through multiple rounds of iterations, the optimal parameter combination that makes the comprehensive evaluation score reach the expected target can be found. Assuming that through optimization, the inclination angle of the swirl plate is adjusted to 30 degrees, and the spacing of the suppression device is adjusted to 0.5 meters, and finally the comprehensive evaluation score reaches 90 points, the secondary optimization is considered successful.

[0041] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations. In addition, the various different embodiments of the present invention can also be combined arbitrarily, as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for suppressing eddy current in a fluid transport pipeline, characterized in that: include: Establish a mapping model between fluid flow state and eddy current intensity to predict possible eddy currents under different working conditions; Based on the prediction results, a genetic algorithm is used to optimize the sensor layout scheme to obtain the most comprehensive flow state information with the least number of sensors; The optimized sensor arrangement scheme is used to collect real-time flow state data, and the reinforcement learning algorithm is applied to optimize the valve adjustment strategy to suppress vortex and improve transportation efficiency; Based on different fluid types, temperatures and pressure conditions, the strategy model is used to generate the optimal valve adjustment scheme in real time; Real-time monitoring of pipeline vibration caused by valve adjustment. When the vibration amplitude exceeds the preset threshold, the safety mechanism is triggered to limit the valve adjustment amplitude. A trade-off model between energy loss and transport efficiency is constructed, and a multi-objective optimization algorithm is applied to solve the model to obtain the optimal regulation strategy that balances eddy current suppression and transport efficiency improvement. A vortex suppression effect evaluation model is established to quantitatively evaluate the vortex suppression effect. If the effect does not meet expectations, the secondary optimization of the adjustment strategy is initiated.

2. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The establishing of the mapping relationship model between the fluid flow state and the eddy current intensity comprises: Obtain density, viscosity, and specific heat capacity data of fluids; Use computational fluid dynamics software to perform numerical simulations to obtain velocity distribution, pressure distribution data, vortex distribution, and turbulence intensity data of the flow field; Preprocess the data and extract key features as model input; A support vector regression algorithm or a multi-layer perceptron neural network algorithm is used to train and establish a mapping relationship model between flow state and eddy current intensity.

3. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The method of optimizing the sensor arrangement scheme by using a genetic algorithm comprises: Establish a numerical simulation model of pipeline flow state and obtain the flow state distribution information inside the pipeline; Clustering algorithms are used to divide different flow state areas and determine key monitoring areas; Construct the code for the sensor deployment plan; Design a fitness function that takes into account the number of sensors, measurement coverage quality, cost, and vibration sensor placement; Genetic algorithm is used to iteratively search for the optimal layout solution.

4. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The application of reinforcement learning algorithm to optimize valve regulation strategy includes: Construct a simulation environment to simulate the fluid transport process; Set the optimization goal and quantify it as a reward function; Use deep reinforcement learning algorithms to build intelligent agent models; The agent continuously interacts with the environment in the simulation environment to learn the optimal control strategy; Deploy the optimal control strategy to the actual system and dynamically adjust the valve opening according to real-time data.

5. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The real-time monitoring of pipeline vibration caused by valve adjustment includes: Acquire a vibration signal collected by a vibration sensor; Extract features from vibration data and calculate vibration amplitude; comparing the vibration amplitude to a preset threshold; If the vibration amplitude exceeds the threshold, the safety protection mechanism is triggered to limit the valve adjustment amplitude and reduce pipeline vibration by optimizing the valve adjustment strategy.

6. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The energy loss and transport efficiency trade-off model is constructed, including: Establish a mathematical model for the trade-off between eddy current suppression and transport efficiency; Use particle swarm optimization algorithm or genetic algorithm to solve the model and obtain the Pareto frontier or Pareto optimal solution set; The optimization results are analyzed to obtain the optimal regulation strategy that balances eddy current suppression and transport efficiency.

7. The method for suppressing eddy current in a fluid transport pipeline according to claim 1, characterized in that: The method of establishing an eddy current suppression effect evaluation model comprises: Obtain eddy current related data collected by sensors; Preprocess the data; Calculate the percentage reduction of eddy current intensity, the percentage increase of transport efficiency and the percentage reduction of energy loss; The three indicators are weighted and summed to obtain a comprehensive evaluation score; If the score is lower than the preset threshold, the secondary optimization of the regulation strategy is triggered, and the particle swarm optimization algorithm is used to optimize the eddy current control parameters.

8. The method for suppressing eddy current in a fluid transport pipeline according to claim 7, characterized in that: The use of a particle swarm optimization algorithm to optimize eddy current control parameters refers to using a particle swarm optimization algorithm to take improving the comprehensive evaluation score as the optimization goal, optimizing the eddy current control parameters through iterative search, and obtaining the optimal parameter combination that enables the comprehensive evaluation score to reach the expected target after multiple rounds of iterations.

9. The method for suppressing eddy current in a fluid transport pipeline according to claim 6, characterized in that: In the mathematical model for trade-off optimization of eddy current suppression and transport efficiency, an eddy current suppression factor and a transport efficiency factor are set as optimization targets; the multi-objective optimization model is converted into a standard form so that it can be solved by an optimization algorithm.

10. The method for suppressing eddy current in a fluid transport pipeline according to claim 3, characterized in that: The iterative search for the optimal arrangement scheme using a genetic algorithm comprises: Genetic algorithm is used to optimize the sensor layout scheme, and the population size, crossover probability and mutation probability are set. The optimal layout is iteratively searched through selection, crossover and mutation operations. The change amplitude of fitness value in multiple consecutive iterations is less than a certain threshold value as the convergence condition of genetic algorithm, and the optimal sensor layout plan at this time is output.

Images