A Method for Constructing a Digital Twin and Evaluating the State of a Fluidization System

Abstract

The present invention relates to the technical field of electronic digital data processing, and discloses a method for constructing a digital twin and evaluating the state of a fluidization system, including: performing CFD solutions on various gas-solid fluidization working conditions to establish a numerical simulation database; determining a core reward function and physical constraints according to the characteristics of the gas-solid fluidization system, training a reinforcement learning agent, and establishing a digital twin model base of the fluidization system; constructing a fluidization system environment according to the twin target, calculating the distribution of multiple physical fields and the evolution of the discrete particle state at subsequent moments; using a multi-disciplinary fusion degradation model to analyze the stress conditions of the materials at each position within a selected time period, calculating the material fatigue and progressive loss rate, and performing system state evaluation to output the results. It solves the problem that it is difficult to balance the simulation accuracy and efficiency of the fluidization system in the prior art, and achieves the purposes of high-efficiency and accurate simulation, high operating reliability, comprehensive evaluation and analysis, convenient maintenance, and high safety.

Description

Technical Field

[0001] The present invention relates to the field of physical technologies, and particularly to electronic digital data processing. Background Art

[0002] Fluidization systems are widely used in many engineering industries such as energy, chemical engineering, mining, metallurgy, food, pharmaceuticals, and biology, such as fluidized bed boilers, pneumatic conveying, and particle spray coating in food and pharmaceuticals. The fluidization technology can effectively improve the utilization rate of raw materials; however, due to the extremely complex fluidization system, involving complex interactions between multiple physical fields, and the multi-phase flow parameters themselves are difficult to measure, and the system opacity is relatively high, there is still great room for improvement in the design, operation, and maintenance of such systems. Simulation can provide more refined guidance for the operation and adjustment of fluidization systems, while the existing CFD (Computational Fluid Dynamics) simulation methods are slow, lack key models, and have poor accuracy. Therefore, when using the results of existing CFD technologies as the data source for digital twins, it often leads to distorted prediction results, so it cannot be used as a direct tool for establishing digital twins. At the same time, fluidization systems are prone to material deterioration due to reasons such as thermal stress and particle erosion, and it is necessary to evaluate their reliability in a timely manner; and this problem involves multiple disciplines, and it is difficult to achieve only relying on CFD technology.

[0003] For example, a Chinese patent with the publication number CN112546971B discloses a dense-phase fluidization reaction control device and method, providing the following technical solutions. The present invention discloses a dense-phase fluidization reaction control device and method, including a dense-phase fluidization reaction gas supply system and a dense-phase fluidization reaction control system. The dense-phase fluidization reaction gas supply system includes a raw material gas I unit, a raw material gas II unit, an inert gas unit, and a dense-phase fluidization reaction gas distribution unit; the dense-phase fluidization reaction control system includes a dense-phase bed fluidization monitoring unit, a fluidization monitoring data calculation and analysis unit, an expert judgment unit, a target controller unit, and other instrument signal units; the present invention also provides a dense-phase fluidization reaction control method with computer autonomous learning, which controls the flow rate and reaction activity of the raw material gas entering the dense phase region of the reactor by analyzing the fluidization characteristics of the reaction bed layer, thereby controlling the dense-phase fluidization reaction process. The present invention has a high degree of automation, efficient and convenient data analysis, and has the characteristics of machine learning, and has broad application prospects in the field of dense-phase fluidization reaction control. However, for the above-mentioned dense-phase fluidization reaction control device and method, the inner cavity volume of the fluidization system is extremely large, and the difficulties in multi-phase flow detection and its accuracy problem cannot be solved by multi-point monitoring; as for the prediction calculation and control process part, it completely depends on the machine learning analysis of the measurement data, and cannot achieve a complete digital twin-level grasp of the system state parameter distribution. Therefore, for scenarios where the operating conditions of the fluidization system change, such as load changes and particle property offsets, it is difficult to achieve a complete description of the fluidization system state through existing analysis and adjustment means, resulting in difficulty in achieving an ideal operating effect. Summary of the Invention

[0004] The present invention solves the problems in the prior art that it is difficult to balance the simulation accuracy and efficiency of the fluidization system, the machine learning model lacks physical mechanisms and has poor extrapolation ability, and the material degradation assessment does not comprehensively cover the multi-field coupling effect through reinforcement learning coupled with CFD. A method for constructing a digital twin and evaluating the state of a fluidization system is proposed, achieving the goals of high-efficiency and accurate simulation, high operating reliability, comprehensive evaluation and analysis, convenient maintenance, and high safety, thereby providing a high-precision and fast-response technical solution for the operation diagnosis of the fluidization system.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for constructing a digital twin and evaluating the state of a fluidization system includes the following steps:

[0007] S1: Perform CFD solutions for various gas-solid fluidization working conditions to establish a numerical simulation database;

[0008] S2: Determine the core reward function and physical constraints according to the characteristics of the gas-solid fluidization system, train the reinforcement learning agent, and establish the base of the digital twin model of the fluidization system;

[0009] S3: Construct a fluidization system environment based on the twin target, and calculate the multi-physical field distribution and the evolution of the discrete particle state at subsequent moments;

[0010] S4: Use a multidisciplinary fusion degradation model to analyze the stress conditions of the materials at each position within the selected time period, calculate the material fatigue and the progressive loss rate, evaluate the system state, and output the results.

[0011] The present invention applies a reinforcement learning paradigm based on CFD to efficiently calculate the multi-physical field distribution and complex particle behavior in the fluidization system environment; considering the multi-physical field effects in the fluidized bed reactor, a multidisciplinary fusion material degradation evaluation method is constructed; the multi-physical field and discrete particle evolution information obtained statistically is combined with the degradation evaluation method to accurately make a reasonable evaluation of the system state, and risk warnings and maintenance suggestions are put forward.

[0012] Preferably, the step S2 includes the following steps:

[0013] S2.1: Based on the characteristics of the fluidization system, select a reinforcement learning algorithm, define the discrete particles as embodied agents, and the flow field and multi-physical fields as the dynamic interaction environment;

[0014] S2.2: Construct the particle state space and the action space;

[0015] S2.3: Design a core reward function based on the energy-minimized multi-scale model, with the normalized suspension transportation energy consumption as the optimization target and adding physical constraint conditions;

[0016] S2.4: Construct a priority experience replay pool based on the numerical simulation database and perform dynamic sampling. When the model meets the conditions, complete the construction of the digital twin base.

[0017] By embodying the discrete particles as agents, the deep integration of physical mechanisms and reinforcement learning is realized. The physical constraint reward function designed in combination with the energy-minimized multi-scale model not only ensures the physical rationality of the calculation process but also realizes the accurate mapping of the complex behavior of the fluidization system.

[0018] Preferably, the physical constraint conditions include particle packing constraints, grid crossing scale constraints, and particle event constraints. The particle packing constraint specifically means that the particle volume fraction does not exceed the close-packed limit, and the distance between any two particles is not less than the sum of their radii; the grid crossing scale constraint specifically means that the particle displacement within a single time step is less than the grid size where the particle is located; the particle event constraint specifically means that each particle undergoes at most one state transition within a single time step.

[0019] Adopting a triple physical constraint mechanism, the particle packing constraint effectively avoids non - physical particle penetration phenomena. The mesh crossing constraint ensures the numerical stability of spatio - temporal discretization, and the particle event constraint precisely controls the frequency of state transitions. The synergistic effect of the three significantly improves the computational accuracy of the digital twin and solves the technical bottlenecks of strong mesh dependence and high risk of computational divergence in traditional CFD.

[0020] Preferably, in step S3, it includes initializing the fluidized system to be simulated, obtaining the discrete particle state at the current moment, and starting time advancement; obtaining particle actions using agents according to the multi - physical field environment; updating the discrete particle state at the next moment, interacting with the multi - physical field environment, and updating the field distribution; continuing time advancement until the end point of the simulation.

[0021] A closed - loop iterative spatio - temporal advancement mechanism is constructed. Through the bidirectional coupling of agent decision - making and multi - physical field update, dynamic interactive simulation of the fluid - solid coupling process is achieved, significantly improving the computational accuracy.

[0022] Preferably, in step S2.3, the energy - minimum multi - scale model takes the normalized suspension transportation energy consumption as the optimization target, where the suspension transportation energy consumption is jointly determined by the density difference between particles and gas, the difference in volume fractions of dense - phase and dilute - phase particles, the proportion of the dense - phase volume, and the gas velocity term.

[0023] Preferably, step S4 includes the following steps:

[0024] S4.1: Based on the discrete particle evolution data, analyze particle impact events near the area of interest including the inner wall and internal components of the fluidized system, and calculate stress, wear probability, and wear amount.

[0025] S4.2: Calculate the thermal stress, and determine whether there is stress concentration or environmental factor influence. If so, enter step S4.3; if not, enter step S4.4.

[0026] S4.3: Calculate the material strength reduction coefficient, output the total stress based on the material strength reduction coefficient, and enter step S4.5.

[0027] S4.4: Output the total stress based on the stress.

[0028] S4.5: Evaluate the state of the fluidized system.

[0029] The intelligent discrimination of complex working conditions is realized through a step - by - step decision - tree structure. By introducing the dynamic calculation of the material strength reduction coefficient, the multiple influences of structural defects and environmental corrosion are effectively integrated, solving the technical problem of stress evaluation distortion in traditional single - field analysis.

[0030] Preferably, step S4.1 includes the following steps:

[0031] S4.11: Calculate the particle event stress, and determine whether there is a non-contact field effect. If so, proceed to step S4.12; if not, proceed to step S4.13;

[0032] S4.12: Calculate the non-contact field acting force, and use the sum of the particle event stress and the non-contact field acting force as the result to replace the particle event stress for subsequent calculations;

[0033] S4.13: Calculate the material wear amount.

[0034] Preferably, the evaluation of the fluidization system state specifically includes: determining the corresponding maximum cycle number according to the stress amplitude at each position, determining the initial thickness of the material structure corresponding to each position, normalizing the calculated stress cycle number and progressive wear amount to obtain a set of state evaluation values of the fluidization system. When the stress cycle number in a local area approaches the limit value given based on the material, or its wear rate is higher than the given limit value, a risk reminder is given to the operation or management personnel.

[0035] Through the dual determination of the stress cycle ratio and the wear rate threshold, multi-dimensional early warning of material failure risks is achieved. The use of a dynamic safety factor mechanism to replace the fixed threshold significantly improves the working condition adaptability of the state evaluation, and can effectively avoid false alarms and missed alarms especially in the variable load operation scenario.

[0036] Preferably, the material wear amount is included in the progressive loss rate statistics and is accurately calculated using the finite element method according to the applied stress, or calculated using the fragmentation kernel function and the sub-particle distribution function model; the material strength reduction coefficient includes magnifying the stress effect in the stress concentration area according to the reduction rate, and for environmental factors, based on the multi-physical field distribution evolution data, marking the oxidation-reduction range of each area, calculating the slagging and corrosion rates, obtaining the change curve of the material strength reduction coefficient over time, and magnifying the stress effect in this area according to the changing reduction rate.

[0037] Preferably, the state space includes particle position, particle velocity, gas velocity, and attribute parameters, and the action space includes displacement change, velocity adjustment, and attribute change.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows.

[0039] 1. Through the integration of reinforcement learning and CFD, the present invention optimizes the problems of high computational resource consumption and low parallel efficiency in traditional numerical simulations. Based on embodied intelligent modeling at the particle scale, a multi-physical field update mechanism is established under physical constraint conditions, and the sample utilization rate is improved by combining experience replay technology. Compared with traditional CFD methods, the present invention significantly shortens the simulation time while maintaining the analysis accuracy, making it possible to monitor industrial-scale fluidization systems in real time and effectively balancing the engineering contradiction between accuracy and efficiency.

[0040] 2. By transforming the energy minimization principle of the fluidization system into a reinforcement learning reward function, the present invention constructs a mechanism and data dual-driven modeling framework. Based on the state and action spaces defined by particle kinematics and integrating the environmental interaction rules of the EMMS mesoscale theory, the machine learning process has a clear hydrodynamic basis. This training mechanism under physical constraints improves the generalization ability of the model under variable operating conditions and provides a more reliable decision-making basis for the operation and maintenance of industrial systems.

[0041] 3. The present invention integrates multi-disciplinary models such as fluid-structure interaction, thermodynamics, and chemical kinetics to construct a structural integrity assessment framework covering multiple factors such as mechanical stress, thermal stress, and environmental impact. Through multi-physical field superposition analysis and the application of dynamic reduction coefficients, the comprehensiveness of degradation prediction is significantly improved, and it can effectively identify complex damage modes that are easily overlooked by traditional single models, providing more accurate spatio-temporal early warnings for preventive maintenance. Description of the Drawings

[0042] Figure 1 It is the overall flowchart of a method for constructing a digital twin and evaluating the state of a fluidization system according to the present invention.

[0043] Figure 2 It is the calculation flowchart of a multi-disciplinary integrated degradation model of a method for constructing a digital twin and evaluating the state of a fluidization system according to the present invention.

[0044] Figure 3 It is the graph of the total coal feeding amount change under variable load operation of a method for constructing a digital twin and evaluating the state of a fluidization system according to the present invention.

[0045] Figure 4 It is the comparison graph of the operating value and the twin value of the bed material temperature at the rear wall under variable load of a method for constructing a digital twin and evaluating the state of a fluidization system according to the present invention.

[0046] Figure 5 It is the graph of the inner wall state evaluation result of the fluidization system in operating mode A of a method for constructing a digital twin and evaluating the state of a fluidization system according to the present invention.

[0047] Figure 6It is the evaluation result diagram of the inner wall state of the fluidization system in operating mode B of the digital twin construction and state evaluation method for a fluidization system of the present invention. Detailed implementation manners

[0048] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following will further describe the embodiments of this disclosure in detail with reference to the accompanying drawings. The proportions of the components are not drawn according to the actual proportions, and the proportions and dimensions shown in the drawings should not limit the essential technical solutions of the present invention. These embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described.

[0049] See Figure 1-6 As shown, a digital twin construction and state evaluation method for a fluidization system includes the following steps:

[0050] S1: Perform CFD solutions for various gas-solid fluidization working conditions to establish a numerical simulation database;

[0051] S2: Determine the core reward function and physical constraints according to the characteristics of the gas-solid fluidization system, train the reinforcement learning agent, and establish the base of the digital twin model of the fluidization system;

[0052] S3: Construct the fluidization system environment according to the twin target, and calculate the distribution of multiple physical fields and the evolution of discrete particle states at subsequent moments;

[0053] S4: Use the multi-disciplinary fusion degradation model to analyze the stress conditions of the materials at each position within the selected time period, calculate the material fatigue and progressive loss rate, conduct system state evaluation, and output the results.

[0054] As Figure 1 In Figure 2 In an embodiment shown, Figure 1 It is the overall flowchart of the digital twin construction and state evaluation method for a fluidization system of the present invention, Figure 2 It is the calculation flowchart of the multi-disciplinary fusion degradation model of the digital twin construction and state evaluation method for a fluidization system of the present invention. The present invention relates to a digital twin construction and state evaluation method for a fluidization system, including the following steps:

[0055] Step 1: Construction of the numerical simulation database

[0056] Perform numerical solutions for various gas-solid fluidization working conditions based on CFD technology, establish a numerical simulation database including the distribution of multiple physical fields and particle motion characteristics, and obtain high-precision data through fine grid division.

[0057] Step 2: Construction and training of the reinforcement learning model

[0058] Algorithm framework definition: Select reinforcement learning algorithms including but not limited to DQN, DDPG, or SAC. Define discrete particles as embodied agents, and the flow field and multi-physical fields as the dynamic interaction environment. Define the state and action spaces: The state space includes particle position, velocity, gas velocity in the grid where the particle is located, and particle attributes; The action space includes displacement change, velocity adjustment, and attribute change.

[0059] Design the reward function, based on the Energy-Minimization Multi-Scale (EMMS) model, with the normalized suspension transportation energy consumption as the optimization goal. And impose physical constraints, including:

[0060] Particle packing constraint: The volume fraction of particles in the grid ≤ the close-packed limit, and the distance between any two particles ≥ the sum of their radii;

[0061] Grid crossing constraint: The displacement of the particle in a single time step < the grid size;

[0062] Particle event constraint: At most one state transition within a single time step.

[0063] Construct a prioritized experience replay pool based on the numerical simulation database, and complete the construction of the digital twin base when the model prediction error is less than the set value.

[0064] Step 3: Real-time simulation and multi-field coupling calculation

[0065] Initialize the system and load the initial state parameters of the target system; Obtain the particle actions through the agent policy function; Update the particle state and solve the NS equation to update the gas-phase field distribution; Iterate until the end of the simulation cycle, and synchronously record the multi-physical field distribution and the particle motion trajectory.

[0066] Step 4: Multidisciplinary integrated material degradation assessment

[0067] According to whether there is a non-contact field effect, calculate the stress and material wear, and calculate the thermal stress. Make corrections based on stress concentration and environmental factors: Calculate the material strength reduction factor for the stress concentration area and the environmental correction area.

[0068] State assessment and decision-making, match the material S-N curve to obtain the maximum number of cycles, calculate the cumulative damage; Normalize the wear and give corresponding alarms.

[0069] In this embodiment, specifically as follows: Use a fine grid and an accurate model, invest sufficient computing power to perform CFD numerical simulation calculations for multiple fluidization conditions, and establish a database. Regarding the model: It is sufficient to obtain accurate numerical simulation results of the fluidization process for constructing the database and can be applied to the present invention. In the present invention, three embodiments are exemplified:

[0070] Example 1: Using the Fully Resolved Simulation (FRS), also known as the True Direct Numerical Simulation (True DNS) method, the grid scale is divided below the particle scale to perform multiphase direct numerical simulation at the sub-particle scale.

[0071] Example 2: Using the DNS (Direct Numerical Simulation) method, the grid scale is divided to the turbulent Kolmogorov dissipation scale, and at the same time, discrete particles are regarded as point sources or pseudo-fluids for solution.

[0072] Example 3: Using the Large Eddy Simulation method or solving the Reynolds-Averaged Navier-Stokes Equations on a coarser grid is also acceptable, which does not affect the applicability of the method, but the data accuracy will decrease accordingly.

[0073] Applying the reinforcement learning paradigm in CFD, establishing the digital twin base, and using a series of physical mechanisms such as the principle of minimum energy as the training objectives and constraints can effectively improve the model accuracy, accelerate the convergence rate, and enhance the interpretability. The detailed description of the adaptability of reinforcement learning (RL) and the fluidization system is as follows:

[0074] The fluid flow field (distribution) is regarded as the environment; discrete particles are regarded as (embodied) agents, and the value ranges of various attribute variables (particle size, velocity, temperature, composition, etc.) of discrete particles are the state space. The interaction between the airflow and discrete particles corresponds to the interaction between the environment and the agent. Among them, the airflow dragging the particles (the action of the environment on the agent) determines the action of the particles, and the particles blocking the airflow (the action of the agent on the environment) can be described as the result of performing an action in the current state. According to the action, the state parameters of the agent change within the state space range (old state + action = new state, and both the old and new states should fall within the state space). Therefore, in the solution process, physical constraints must be imposed on the actions of the agent.

[0075] The present invention has no special requirements for the RL algorithm, and common algorithms such as Q-Learning, DQN (Deep Q-Network), SAC (Soft Actor-Critic), DDPG (Deep Deterministic Policy Gradient), and Dyna-Q are all applicable.

[0076] It should be noted that there are various classification methods for RL. Considering that the problem of describing the fluidization system to be solved is a real and mechanistic industrial process, it can also be discussed under the classification of model-based and model-free reinforcement learning. The technical route of the present invention is applicable to both types of reinforcement learning methods.

[0077] Discrete particles are regarded as agents, and the calculation of particle motion is regarded as a Markov Decision Process (MDP). During the process of training the agent, the elements used are as follows:

[0078] (1) Objective function: The principle of minimum energy, that is, the energy consumption for suspended transportation of particles per unit mass tends to be minimized, Nst -> min.

[0079] In this embodiment, the calculation method of the suspended transportation energy used refers to the energy-minimization multi-scale model (EMMS).

[0080] (2) State space S, which includes the spatial position of the particle, the particle velocity, the gas velocity at the position where the particle is located, and other user-defined variables.

[0081] More variables Ψ can be added to the state space according to the actual problem, such as discrete particle information such as diameter and density in a polydisperse particle system, the particle component composition, temperature, turbulent kinetic energy, etc. in a chemical reaction system.

[0082] (3) Action space A, which includes the particle movement distance, the change value of the particle velocity, and the change amplitude of other user-defined variables, and is jointly determined by the current state St of the agent and the state space S.

[0083] Specifically: "Physical constraints" can be referred to.

[0084] (4) Reward function rt, whose expression is a function of the suspended transportation energy from the starting moment of reward accumulation to the current moment and the cumulative reward decay factor.

[0085] Regarding the reward function and normalization, in RL, the reward function is the most core, but its given method can also be freely designed (taking AlphaGo as an example, the design method of the reward function does not affect the achievement of the goal of "playing Go", but only affects the trend of the chess game). Therefore, the highlight of the present invention is to use the "principle of minimum energy" to design the reward function. As for what kind of normalization method to adopt and what the reward decay for each step is, they are relatively free. In this embodiment, the decay factor used is 0.80 - 0.99.

[0086] ((X) Physical constraints:

[0087] Granular packing constraint: for any grid, the volume fraction of the granules therein is not greater than its packing limit: ε s ≤ε s,cp ,

[0088] wherein, ε is the volume fraction of the granules, and the subscript s means the solid phase solid, and cp represents the close - packing limit of the granules (generally taken as about 0.63 for single - sized spherical granules).

[0089] For any two granules, the distance between the coordinates of their centroid positions is not less than the sum of the radii of the two granules. It is assumed that all granules are spherical and no extrusion deformation occurs. Wherein, D ij is the distance between the centers of the spheres of the two granules numbered i and j , and d is the granule diameter.

[0090] Processing method when the constraint is not satisfied:

[0091] It can be processed as if the granules collide. It is considered that the granules collide and generate displacements (state changes). Hard - sphere, soft - sphere and other models can be used for calculation to update the granule state. Because distance detection is included in such models, it can ensure that the new state obtained after calculation satisfies the constraint conditions.

[0092] It is also possible to adopt a simplified processing method for the above - mentioned collisions. For example: referring to the processing method of the multiphase particle - in - cell method (MP - PIC), instead of directly calculating the granule collisions, a volume force is directly applied to the granules along the direction of the granule stress gradient, causing them to displace (the result is also a state change, which can also be called position offset or state offset), so that the state of the displaced granules (agents) satisfies the packing constraint. The method of giving the volume force is not uniquely determined and can refer to the existing technologies.

[0093] Grid crossing scale constraint: within any time step, the movement distance of any granule is less than the size of the current grid where it is located. This constraint is a direct constraint on the time slot. If it is not satisfied, the time slot can only be reduced until the movement distance of the granule within a single time slot satisfies the constraint.

[0094] Granular event constraint: in the time scale of one action and interaction, each granule undergoes at most one state change, and each state change is not the superposition of the effects of two state changes.

[0095] Explanation of the granular event constraint:

[0096] This constraint is similar to the grid-crossing scale constraint, and its original intention is to limit the time slot used to divide the continuous time flow in the RL paradigm. The grid-crossing scale constraint is a limitation on the single-movement distance of particles (agents), and the particle event constraint mainly limits the number of particle events (such as collisions), usually limited to 1 time. Within each time slot, the agent's behavior and the environmental state are sampled and updated, which can be understood as "taking a photo". It is similar to the concept of time step in simulation calculations.

[0097] Construct a fluidized system environment for the twin target, and calculate the distribution of multiple physical fields and the evolution of discrete particle states during time advancement. Proceed as follows:

[0098] Determine the state space S, action space A, and reward function R of the solid-phase particles (agents);

[0099] Put part of the particle information (s, a, r, s’) in the database into the experience replay pool;

[0100] The present invention has no special requirements for the sampling method, and existing technologies can be referred to.

[0101] Initialize the fluidized system to be simulated, and obtain the discrete particle state s at the current moment t , start time advancement; according to the multi-physical field environment, use the agent to obtain the particle action a t ; update the discrete particle state s at the next moment t+1 , interact with the multi-physical field environment, and update the field distribution; continue time advancement until the end point of the simulation.

[0102] By statistically calculating the stress on the local area material during the operation process, progressively calculate the material loss rate x:

[0103] When applying this degradation model for analysis, the fatigue characteristics of the corresponding material should be determined first. Specifically:

[0104] The structural material of the fluidized system is generally steel. According to the evolution of the multi-physical field distribution in the fluidized system and the calculation results of particle impact events, the alternating stress on the material is much lower than the yield limit of the material, and it is determined to belong to high-cycle fatigue. For the material types used in the fluidized system (such as: 20# steel, heat-resistant steel, stainless steel, carbon steel, alloy, etc.), the fatigue characteristics of the material can be determined according to its S-N curve.

[0105] When using the S-N curve, the corresponding fatigue life (N, number of cycles) can be found according to the stress amplitude (S).

[0106] The stress F on the material at any position can be expressed as the superposition of the following several effects. Specifically:

[0107] ① Particle event stress part (F1)

[0108] Based on the discrete particle evolution data, analyze the particle impact events near the areas of concern such as the inner wall surface and internal components of the fluidization system, and calculate the stress, wear probability, and wear amount.

[0109] In the case of no non-contact field acting force:

[0110] The impact stress F1 is calculated according to the energy conservation and momentum balance of dynamics, and analyzed and calculated according to elastic / inelastic collision; the wear probability P x and the wear amount x are included in the progressive wear rate statistics. The finite element method can be used for accurate calculation according to the stress received, or it can be simplified to a kind of fragmentation process, and the fragmentation kernel function and sub-particle distribution function model are used for calculation.

[0111] At the event level, it mainly includes the following data: occurrence time, particle diameter, impact angle, relative velocity before and after the impact event;

[0112] At the statistical level, it mainly includes the following data: particle material, hardness, sphericity, collision frequency, average momentum loss.

[0113] In the case of having non-contact field acting force: Use F1 + F2 for the calculation of the wear probability P x and the wear amount x.

[0114] ② Non-contact field acting part (F2)

[0115] If the electrostatic effect between particles and the wall surface, or between particles in the fluidization system is significant, or there are non-contact field actions such as magnetic field and electric field, then based on the field acting force data (or field strength and particle charge data), before the stress obtained in ① is incorporated into the fatigue characteristics calculation of the S-N curve, superimpose the increase or decrease value of the true collision stress caused by the non-contact field acting force F2, and then perform the material strain and fatigue characteristics calculation.

[0116] ③ Thermal stress part (F3)

[0117] Based on the multi-physical field distribution evolution data, calculate the thermal stress F3 of the materials at various places in the fluidization system.

[0118] It is mainly calculated according to the temperature distribution. The local structure can be simplified for direct calculation. For example, the one-dimensional fully constrained plane stress can be written as: thermal stress = elastic modulus × linear expansion coefficient × temperature change. A more rigorous approach is to perform a finite element simulation of elastic mechanics on the real structure based on the known temperature distribution.

[0119] In addition, in special cases, the material strength reduction coefficient a should also be defined:

[0120] ① Stress concentration and organizational defect part (a1)

[0121] Locate the stress concentration areas according to the fluidization system design and construction drawings, mainly including the pipe connection turning points, wall areas with protrusions or notches, and internal components.

[0122] Define the material strength reduction coefficient a1 for this area, and magnify and calculate the stress effect on this area according to the reduction rate.

[0123] The reduction coefficient value can be manually defined from the perspective of safe use; or the finite element simulation method can be used to calculate the true stress conditions at the defect under several working conditions according to the real defective structure, and a reduction coefficient value or function more in line with the actual situation can be obtained by fitting.

[0124] ② Environmental factor part (a2)

[0125] Based on the multi-physical field distribution evolution data, mark the oxidation-reduction atmosphere of each area, calculate the slagging and corrosion rates, obtain the change curve of the material strength reduction coefficient a2 with time advancement, and magnify and calculate the stress effect on this area according to the changing reduction rate. If there are other coatings such as metal spraying and high-temperature coatings, this part will be calculated again when the real-time progressive wear amount exceeds the coating thickness. The slagging problem can be simplified and calculated using the "collision + probability adhesion + accumulation" model. For the corrosion problem, the corrosion rate can be estimated according to the gas component concentration distribution and empirical formula.

[0126] The present invention does not exclude any slagging and corrosion model or calculation method, because the multi-physical field distribution evolution data has been obtained in the previous steps, which is sufficient to meet the calculation requirements of different precision models.

[0127] Evaluate the state of the fluidization system based on the calculated material fatigue and progressive loss rate, and issue instructions or suggestions.

[0128] Evaluation steps:

[0129] I. Material fatigue: Determine the corresponding maximum number of cycles N according to the stress amplitude at each position max ;

[0130] Material wear: Determine the initial thickness c of the material structure corresponding to each position ini .

[0131] For the case where the stress amplitude span is large, N can be estimated by interpolation, fitting, etc. max .

[0132] II. At any concerned moment t, for the calculated number of stress cycles N t and progressive wear amount c tNormalization is performed to obtain a set of state evaluation values of the fluidization system at time t, and the evaluation value set should consist of at least fatigue evaluation and wear evaluation;

[0133] There can be various normalization methods in this embodiment, and reference can be made to the prior art.

[0134] III. Customization: Decision interval (segmented) or safety factor (one-size-fits-all), used to determine when to issue what kind of instructions or strategies. That is, when the stress cycle times in a local area approach the limit value given based on the material S-N curve, or its wear rate is higher than the given limit value, a risk reminder is sent to the operation or management personnel.

[0135] In this embodiment, the safety factor mode is used:

[0136] If it is considered that there is a risk of local material structure fracture when N t / N max > 0.8, then 0.8 (or a smaller value) is defined as the stress fatigue safety factor y. When N t / N max ≥ y, a structural fatigue maintenance reminder is issued.

[0137] In actual operation, different safety factors can be defined according to the structure and material characteristics of each position, as well as the requirements of the operation safety margin.

[0138] Taking the wear evaluation as an example again, the decision interval mode is used:

[0139] If it is considered that there is a possibility of a boiler shutdown accident when the water wall position has c t / c ini > 0.3, then the following evaluation configuration can be carried out:

[0140] Decision interval: c t / c ini = 0 ~ 0.1,

[0141] Strategy: Only dynamically update the visualization effect and do not mark it as a risk item;

[0142] Decision interval: c t / c ini = 0.1 ~ 0.2,

[0143] Strategy: Mark it as a risk item, estimate the remaining reliable operation time (using methods such as polynomial extrapolation and prediction simulation), send it to the management / operation personnel, and arrange a maintenance plan;

[0144] Decision interval: c t / c ini = 0.2 ~ 0.3,

[0145] Strategy: Key maintenance reminder;

[0146] Decision interval: c t / c ini > 0.3,

[0147] Strategy: Major operation risk warning.

[0148] In actual operation, different decision intervals can also be defined for materials at different positions. For example, the alarm threshold can be increased for materials at non-critical positions (the importance of other walls must be lower than that of the water circulation tube bundle) to avoid over-maintenance and waste of maintenance efforts.

[0149] The following is the application situation of this embodiment:

[0150] 1. Fluidization system operation analysis - Laboratory scale

[0151] Taking the riser of a circulating fluidized bed as an example, the particle mass flow rate at the outlet directly reflects the transport capacity of the fluidizing air (gas) for solid particles and can prove whether the simulation analysis results are accurate.

[0152] Apply the present invention to a laboratory-scale riser with a diameter of 0.09 m and a height of 10.2 m. The diameter of the solid particles is 54 um and the density is 930 kg / m 3 . Select a total of 6 working conditions with fluidization air velocities Ug of 1.52 m / s and 2.10 m / s and material amounts of 15 kg, 25 kg, and 35 kg respectively. The calculation results are shown in Table 1.

[0153] It can be seen that the accuracy of the analysis results of the existing CFD technology is low (in six working conditions, at most, the particle mass flow rate is overestimated by 973%); while the accuracy of the present invention is significantly improved.

[0154] Table 1

[0155]

[0156] Table 2

[0157]

[0158] Table 1 and Table 2 are for U gComparison of calculation effects at different values. The source of experimental data exp.: Li J H, Tung Y, Kwauk M. Axial voidage profiles of fast fluidized beds in different operating regions. Proceedings of the Second International Conference on Circulating Fluidized Beds, Compiégne, France, 193 - 203, 1988 (Li Jinghai, et al. Axial voidage profiles of fast fluidized beds in different operating conditions. The Second International Conference on Circulating Fluidized Beds, Compiégne, France, 193 - 203, 1988).

[0159] 2. Operation analysis of fluidization system - industrial scale

[0160] For a 130t / h cogeneration fluidized bed boiler, the change in the total coal feed under variable load operation on the demand side is as Figure 3 (the data sampling time interval is 1 min). The bed material temperature at the rear wall can reflect the fluidization and combustion organization in the furnace. The comparison between the measured operating values and the calculated values of the twin is as Figure 4 .

[0161] 3. Analysis of material deterioration in fluidization system

[0162] Using different operating modes (A - hot state, B - cold state), the visualized results after quantifying the inner wall state assessment of the fluidization system are as Figure 5 、 6 shown. The darker the color, the more serious the deterioration. It can be seen from the comparison that particle impact is still the main reason for the material deterioration of the system. However, the influence of thermal stress, non - contact force field and environmental factors on the deterioration makes the material deterioration results calculated purely based on particle collision significantly distorted. Under the calculation system proposed in the present invention, the assessment of material deterioration in the fluidization system under the coupling action of multiple fields can be effectively realized; and the present invention applies the reinforcement learning paradigm in the original CFD architecture, with high calculation efficiency, meeting the dual requirements of the digital twin for response efficiency and calculation accuracy, and can effectively realize the "transparency" of the industrial fluidization system, providing a reliable guarantee for its stable operation and efficient maintenance.

[0163] The present invention is not limited to the above - mentioned embodiments. No matter what changes are made in its shape or material composition, as long as the structural design provided by the present invention is adopted, it is a deformation of the present invention and should be considered within the protection scope of the present invention.

Claims

1. A method for constructing a digital twin and evaluating the state of a fluidization system, characterized in that It includes the following steps: S1: Conduct CFD solutions for various gas-solid fluidization working conditions to establish a numerical simulation database; S2: Determine the core reward function and physical constraints according to the characteristics of the gas-solid fluidization system, train the reinforcement learning agent, and establish the digital twin model base of the fluidization system; S3: Construct the fluidization system environment according to the twin target, calculate the multi-physical field distribution and the evolution of the discrete particle state at subsequent moments; S4: Use the multi-disciplinary fusion degradation model to analyze the stress conditions of the materials at each position within the selected time period, calculate the material fatigue and progressive loss rate, evaluate the system state, and output the results.

2. The digital twin construction and state evaluation method of a fluidization system according to claim 1, characterized in that The step S2 includes the following steps: S2.1: Based on the characteristics of the fluidization system, select the reinforcement learning algorithm, define the discrete particles as embodied agents, and the flow field and multi-physical fields as the dynamic interaction environment; S2.2: Construct the particle state space and action space; S2.3: Design the core reward function based on the energy-minimized multi-scale model, with the normalized suspension transportation energy consumption as the optimization target and add physical constraint conditions; S2.4: Construct a prioritized experience replay pool based on the numerical simulation database and perform dynamic sampling. When the model meets the conditions, complete the construction of the digital twin body base.

3. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 2, characterized in that The physical constraint conditions include particle packing constraints, grid crossing scale constraints, and particle event constraints. The particle packing constraint is specifically that the particle volume fraction does not exceed the close-packed limit, and the distance between any two particles is not less than the sum of their radii; the grid crossing scale constraint is specifically that the particle displacement within a single time step is less than the grid size where it is located; the particle event constraint is specifically that each particle undergoes at most one state transition within a single time step.

4. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 2 or 3, characterized in that In the step S3, it includes initializing the fluidization system to be simulated, obtaining the discrete particle state at the current moment, and starting time advancement; according to the multi-physical field environment, using the agent to obtain the particle actions; Update the discrete particle state at the next moment, interact with the multi-physical field environment, and update the field distribution; continue time advancement until the end point of the simulation.

5. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 2, characterized in that, In the step S2.3, the energy-minimized multi-scale model takes the normalized suspension transportation energy consumption as the optimization target, where the suspension transportation energy consumption is jointly determined by the density difference between the particles and the gas, the difference in the volume fractions of the dense and dilute phase particles, the proportion of the dense phase volume, and the gas velocity term.

6. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 2 or 3, characterized in that The step S4 includes the following steps: S4.1: Based on the discrete particle evolution data, analyze the particle impact events near the concerned areas including the inner wall and internal components of the fluidization system, and calculate the stress, wear probability, and wear amount; S4.2: Calculate the thermal stress, and judge whether there is stress concentration or the influence of environmental factors. If so, enter step S4.3; if not, enter step S4.4; S4.3: Calculate the material strength reduction coefficient, output the total stress based on the material strength reduction coefficient, and enter step S4.5; S4.4: Output the total stress based on the stress; S4.5: Evaluate the state of the fluidization system.

7. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 6, characterized in that In the step S4.1, it includes the following steps: S4.11: Calculate the particle event stress, and judge whether there is a non-contact field effect. If so, enter step S4.12; if not, enter step S4.13; S4.12: Calculate the non-contact field force, and use the sum of the particle event stress and the non-contact field force as the result to replace the particle event stress for subsequent calculations; S4.13: Calculate the material wear amount.

8. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 6, characterized in that, The evaluation of the fluidized system state specifically includes: determining the corresponding maximum cycle number according to the stress amplitude at each position, determining the initial thickness of the material structure corresponding to each position, normalizing the calculated stress cycle number and progressive wear amount to obtain a set of state evaluation values for the fluidized system. When the stress cycle number in a local area approaches the limit value given based on the material, or its wear rate is higher than the given limit value, a risk reminder is given to the operation or management personnel.

9. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 7, characterized in that The material wear amount is included in the progressive loss rate statistics and is accurately calculated using the finite element method according to the stress received, or calculated using the fragmentation kernel function and the sub-particle distribution function model; the material strength reduction coefficient includes amplifying the stress effect in the stress concentration area according to the reduction rate, and for environmental factors, based on the multi-physical field distribution evolution data, marking the oxidation-reduction range of each area, calculating the slagging and corrosion rates, obtaining the change curve of the material strength reduction coefficient over time, and amplifying the stress effect in this area according to the changing reduction rate.

10. A method for constructing a digital twin and evaluating the state of a fluidization system according to claim 2, characterized in that, The state space includes particle position, particle velocity, gas velocity, and attribute parameters, and the action space includes displacement change, velocity adjustment, and attribute change.

Images