Method and system for predicting irreversible loss of centrifugal air compressor of fuel cell

Abstract

The invention belongs to the technical field of fuel cells, and particularly relates to a fuel cell centrifugal air compressor irreversible loss prediction method and system, and the method comprises the steps: collecting performance data based on a fuel cell centrifugal air compressor comprehensive performance test platform, and building and verifying a multi-physics coupling CFD simulation model; defining an irreversible loss type and related structure parameters, constructing an integrated CFD simulation framework, generating a parameter combination table through an orthogonal test, and performing simulation calculation; an RL-GHEM method is provided, the weight and combination strategy of a base model are optimized, linear and nonlinear combination modes are dynamically switched, and irreversible loss prediction models under different working conditions are constructed. The hybrid integrated model based on reinforcement learning guidance is provided, the model combination strategy is dynamically optimized through the reward mechanism, the base model with the optimal performance is optimized, the prediction precision, stability and robustness are improved, precise prediction of the irreversible loss of the air compressor is achieved, and the problem that in the prior art, the prediction precision is insufficient under variable working conditions is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cells, and in particular, relates to a method and system for predicting irreversible losses of a fuel cell centrifugal air compressor. Background Art

[0002] As a clean and efficient energy conversion technology, fuel cell technology plays an important role in global energy transformation and low-carbon economic development. Fuel cells have been widely used in transportation, distributed power generation and portable devices due to their high efficiency and environmental friendliness. Their advantages in realizing green energy utilization are particularly significant. However, in order to achieve the best performance of the fuel cell system, the efficiency of the air supply system becomes one of the key technologies. In the fuel cell system, the efficiency and stability of the air supply system directly affect the performance of the electrochemical reaction and the overall efficiency of the system. The centrifugal air compressor is the core equipment of the fuel cell air supply system, and its performance determines the pressure, flow rate and energy conversion efficiency of the air supply. However, due to the complex and changeable working environment faced by the centrifugal air compressor during operation, its internal flow, thermodynamic and kinetic characteristics are complex and diverse, and different types of irreversible losses are inevitably generated. These losses significantly limit the performance of the compressor and become the main obstacle to further optimization of the fuel cell system.

[0003] The irreversible losses of centrifugal air compressors mainly include the following types: 1. Flow loss: Due to the vortex, flow separation and secondary flow phenomena of the gas in the impeller and diffuser, kinetic energy is converted into thermal energy, and the compression efficiency is reduced. 2. Thermodynamic loss: The entropy increase effect generated during the gas compression process causes part of the energy to be dissipated as heat, thereby reducing the energy conversion efficiency of the system. 3. Mechanical loss: The energy loss caused by friction between bearings, seals and rotating parts has a direct impact on the mechanical efficiency of the compressor. 4. Shock wave loss: Under super-design conditions, local shock waves may be generated in the impeller or diffuser, causing rapid dissipation of energy and decreased efficiency. The causes of the above losses involve complex fluid mechanics and thermodynamic phenomena. Current technologies still face many challenges in predicting and controlling these irreversible losses under variable conditions.

[0004] To reduce these losses, existing technologies mainly focus on the following directions: 1. Geometric design optimization: improving the geometry of the impeller and diffuser to improve compression efficiency. For example, optimizing the curvature of the impeller and the flow channel design of the diffuser can reduce vortex and flow separation. However, this optimization is usually designed for specific working conditions (such as fixed speed, specific flow), and cannot adapt well to changing requirements under dynamic conditions. 2. Advanced control methods: such as model predictive control (MPC) and fuzzy control. These methods use system models or empirical rules to dynamically adjust the operating state of the air compressor. However, these control strategies rely on fixed mathematical models or artificial design rules, and show certain limitations when dealing with strong nonlinear and rapidly changing working conditions. 3. Data-driven optimization: With the application of artificial intelligence and machine learning, many studies have tried to predict the operating state of the compressor and optimize its performance through algorithms. Although these methods show potential in dealing with nonlinear problems, they still have shortcomings in robustness, physical interpretation and adaptability to external disturbances.

[0005] Taking patent CN110826270A as an example, the patent discloses a method for analyzing energy loss during the rotating stall of a centrifugal compressor. Its technical solution analyzes the characteristics of energy loss during the rotating stall of a centrifugal air compressor through a three-dimensional geometric model and a finite element model. Although this method has certain research value, it has the following shortcomings in practical applications: 1. Low computational efficiency: The finite element model is too complex and requires high computing resources, making it difficult to meet real-time optimization needs. 2. Single analysis dimension: It mainly focuses on the total amount of energy loss, and does not refine types such as flow loss and thermodynamic loss. 3. Limited applicability: The model relies on specific modeling assumptions, lacks the ability to adapt across operating conditions, and is difficult to promote and apply in complex dynamic environments.

[0006] Therefore, exploring efficient, accurate and cross-operating-condition adaptability prediction and control methods for the causes of irreversible losses of centrifugal air compressors under variable operating conditions is a key research direction to promote the development of fuel cell air supply system technology. Summary of the invention

[0007] In view of the defects of the prior art, the present invention proposes a method and system for predicting irreversible losses of a fuel cell centrifugal air compressor. The method combines reinforcement learning with a hybrid integration strategy and proposes a hybrid integration model method guided by reinforcement learning, namely RL-GHEM. The combination and selection process of the integrated model is dynamically guided by the reinforcement learning mechanism, and the reward mechanism in reinforcement learning is used to select and combine the base models with the best performance, thereby improving the accuracy, stability and robustness of the overall model prediction, and realizing accurate and reliable prediction of the irreversible losses of the air compressor.

[0008] In one aspect, the present invention provides a method for predicting irreversible losses of a fuel cell centrifugal air compressor, the method comprising:

[0009] Step 1: Based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, the performance data of the air compressor is collected under different boundary parameters, and combined with the three-dimensional geometric model of the centrifugal air compressor, a multi-physics field coupled computational fluid dynamics (CFD) simulation model of the fuel cell centrifugal air compressor is established; the convergence and accuracy of the established CFD simulation model are verified;

[0010] Step 2: Define N types of irreversible loss for different parts of the air compressor, and determine M structural parameters related to the irreversible loss based on the structural characteristics of each part. Based on the CFD simulation model of the fuel cell air compressor, build an integrated CFD simulation framework, determine the number of levels and parameter combinations of the M structural parameters by designing orthogonal experiments, generate a parameter combination table, and import the parameter combination table into the CFD simulation framework. Use the CFD simulation framework to perform simulation calculations on all parameter combinations in the parameter combination table in turn, and extract key data corresponding to each type of irreversible loss from each set of simulation results;

[0011] Step 3: Propose the RL-GHEM method, construct multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and punishment mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy, and construct an irreversible loss prediction model for air compressors under different working conditions.

[0012] Further, step 2 includes:

[0013] Step 2.1: According to the main sources of energy loss in the operation of the air compressor, the irreversible loss types are divided into flow loss, thermodynamic loss, mechanical loss and shock wave loss. According to the influence of different components of the air compressor on the energy loss, the structural parameters that affect the irreversible loss are determined;

[0014] Step 2.2: Import the structural parameters of each air compressor component that affects the irreversible loss determined in step 2.1 as input variables into the CFD simulation model, perform parameterized modeling on the structural parameters, generate multiple CFD simulation models of different working conditions, expand the CFD simulation model according to the analysis requirements of the irreversible loss type, build a multi-physics field simulation framework based on the CFD simulation model, and define the calculation method of each irreversible loss in the multi-physics field simulation framework;

[0015] Step 2.3: Based on the M structural parameters and their levels of each component of the air compressor that affect the irreversible loss, select the corresponding orthogonal table to generate a parameter combination table, automatically import the parameter combination into the CFD simulation model constructed in step 2.2, and perform simulation calculations on all parameter combinations in turn. For each set of simulation results, extract the velocity field, temperature field and other related data, and apply wavelet denoising processing to the data.

[0016] Furthermore, in step 2.1, the structural parameters affecting the irreversible loss include but are not limited to: blade inlet installation angle, blade outlet installation angle, outlet blade thickness, volute cross-section ellipticity, volute outlet diameter, volute tongue angle, diffuser outlet radius, diffuser inlet diameter and diffuser outlet width.

[0017] Furthermore, in step 2.3, the flow loss in the multi-physics simulation framework is expressed by the entropy increase rate caused by viscous dissipation and turbulent dissipation. The entropy increase rate caused by viscous dissipation is determined by the following formula:

[0018]

[0019] Where: s v represents the entropy increase rate caused by viscous dissipation; μ represents the dynamic viscosity; T represents the thermodynamic temperature of the system; τ ij represents the viscous stress tensor; u i represents the velocity component in the i-th direction; x j represents the spatial coordinates of the jth direction; represents the velocity gradient;

[0020] The rate of entropy increase due to turbulent dissipation is determined by:

[0021]

[0022] Where: s v’ represents the entropy increase rate caused by turbulent dissipation; β represents the empirical coefficient; ρ m represents fluid density, reflecting the mass of the fluid per unit volume; k represents turbulent kinetic energy; w represents turbulent frequency; T represents temperature;

[0023] Thermodynamic losses are expressed by the rate of entropy increase due to the temperature gradient, which is determined by the following formula:

[0024]

[0025] Where: s t represents the entropy increase rate caused by temperature gradient; T represents temperature; k e represents the thermal conductivity; represents the temperature gradient; represents the square of the temperature gradient;

[0026] Mechanical losses are expressed by the entropy increase rate due to wall friction, which is determined by the following formula:

[0027]

[0028] Where: s w represents the entropy increase rate caused by wall friction; τ w represents the wall shear stress; v represents the first layer grid velocity near the wall; T represents the temperature;

[0029] The shock wave loss is expressed by the entropy increase rate caused by temperature fluctuations, which is determined by the following formula:

[0030]

[0031] Where: s t‘ represents the entropy increase rate caused by temperature pulsation; λ represents the thermal diffusivity; λ t represents the reference thermal diffusivity; s t It represents the rate of entropy increase caused by temperature gradient.

[0032] Further, step 3 includes:

[0033] Step 3.1: Select multiple types of base models, build a base model library, divide the irreversible loss data into training subsets and test subsets, conduct independent training on each base model on its corresponding training subset, evaluate the performance of each base model on the test subset, calculate the corresponding mean square error, and assign initial weights through the reinforcement learning mechanism based on the evaluation results to complete the initialization of the base model library;

[0034] Step 3.2: Initialize the reinforcement learning controller, set the controller parameters including state information, action set and reward function, receive the state information of the current base model, and the controller generates actions based on the state information. The actions include adjusting the weights of the base model or changing the model combination strategy; calculate the reward signal based on the overall model prediction performance, and optimize the controller strategy through the reinforcement learning algorithm;

[0035] Step 3.3: Monitor the performance of the base models in real time, record the mean square error, computational complexity, and generalization ability, adjust the weights of the base models based on the reward mechanism, optimize the overall model performance by increasing the weights of the base models with good performance or reducing the weights of the base models with poor performance, dynamically select the model combination method based on the real-time data characteristics, and the model combination method includes linear weighted average and nonlinear weighted combination. Apply the updated weight distribution and combination strategy to the hybrid integration model to complete the dynamic adjustment;

[0036] Step 3.4: Set the trade-off strategy between exploration and utilization behavior to determine whether the current state is to perform exploration behavior or utilization behavior. In the exploration phase, expand the search space by randomly perturbing the base model weights or introducing new model combination strategies. In the utilization phase, optimize the overall prediction performance by selecting the current best performing model combination strategy. Dynamically adjust the ratio of exploration and utilization based on historical reward feedback to achieve continuous optimization of the base model configuration and performance improvement.

[0037] Furthermore, the base model in step 3.1 includes but is not limited to a deep neural network, a support vector machine, a classification regression decision tree, and a long short-term memory network.

[0038] Furthermore, in step 3.2, the input controller state information includes the predicted mean square error, weight distribution and historical performance of the base model.

[0039] Furthermore, in step 3.2, the actions generated by the controller include adjusting the weights of the base models and changing the combination strategy of the base models, and the combination strategy is switching between linear weighted or nonlinear weighted combination methods.

[0040] Further, step 1 comprises:

[0041] Step 1.1: Build a comprehensive performance test platform for fuel cell centrifugal air compressors, test the performance parameters, operating parameters and control parameters of centrifugal air compressors under the full range of working conditions, and obtain test data of the air compressors under different working conditions;

[0042] Step 1.2: Use 3D modeling software to construct a 3D geometric model of the centrifugal air compressor;

[0043] Step 1.3: Based on the test data measured in step 1.1 and the three-dimensional geometric model constructed in step 1.2, a multi-physics field coupling calculation CFD simulation model for the fuel cell centrifugal air compressor is established. The key performance parameters are calculated multiple times through the CFD simulation model to complete the convergence verification of the simulation results. The simulation calculation results are compared and analyzed with the test data obtained in step 1.1 to verify the convergence and accuracy of the CFD simulation model.

[0044] On the other hand, the present invention also provides a fuel cell centrifugal air compressor irreversible loss prediction system, comprising:

[0045] The data acquisition and model building module is used to collect the performance data of the air compressor under different boundary parameters based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, and to establish a multi-physics field coupling calculation CFD simulation model of the fuel cell centrifugal air compressor in combination with the three-dimensional geometric model of the centrifugal air compressor, and to verify the convergence and accuracy of the CFD simulation model;

[0046] The parameter optimization and key data extraction module is used to define N types of irreversible loss for different parts of the air compressor, and determine M structural parameters related to the irreversible loss based on the structural characteristics of each part. Based on the CFD simulation model of the fuel cell air compressor, an integrated CFD simulation framework is constructed, and the number of levels and parameter combinations of the M structural parameters are determined by designing orthogonal experiments, and a parameter combination table is generated. The parameter combination table is imported into the CFD simulation framework, and the CFD simulation framework is used to perform simulation calculations on all parameter combinations in the parameter combination table in turn, and key data corresponding to each type of irreversible loss is extracted from each group of simulation results;

[0047] The prediction model construction module is used to propose the RL-GHEM method, build multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and penalty mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, and dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy to construct an irreversible loss prediction model for air compressors under different working conditions.

[0048] The beneficial effects of the present invention are:

[0049] By constructing a test bench for a fuel cell centrifugal air compressor and a CFD simulation model coupled with multiple physical fields, the present invention can realize accurate performance parameter collection and analysis under different boundary conditions, ensuring high fitting degree and high reliability of the model under complex working conditions. Combining experimental verification and CFD simulation verification, the present invention can fully reflect the multidimensional characteristics and dynamic changes in the operation of the air compressor, improve the accuracy of the prediction and the versatility of the model, and lay a solid foundation for the refined management of energy loss.

[0050] By selecting key structural parameters and designing orthogonal experiments, the present invention realizes batch simulation and data preprocessing of multi-dimensional parameter combinations under the CFD integrated simulation framework. Compared with traditional methods, this systematic and efficient loss extraction method can more accurately identify and characterize various sources of irreversible losses, provide detailed data support and optimization paths for subsequent optimization, and improve the overall energy efficiency and operating performance of the air compressor.

[0051] The RL-GHEM method proposed in this paper combines reinforcement learning with a hybrid integrated model, significantly improving the model's prediction accuracy and adaptability to irreversible loss data under different working conditions, and possesses strong learning and self-optimization capabilities. In complex and changeable working conditions, the intelligent control and combination strategy of the RL-GHEM method can achieve continuous optimization of prediction performance, providing more powerful data support and optimization tools for energy management and performance improvement of air compressors. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of the method for predicting irreversible losses of a fuel cell centrifugal air compressor of the present invention;

[0053] Figure 2 2 is a schematic diagram of the layout of a monitoring system for a comprehensive performance test platform for a fuel cell air compressor according to an embodiment of the present invention;

[0054] Figure 3 is a structural schematic diagram of a three-dimensional model of a fuel cell air compressor according to an embodiment of the present invention;

[0055] Figure 4 Schematic diagram of a CFD integrated simulation framework of a fuel cell air compressor according to an embodiment of the present invention;

[0056] Figure 5 4 is a flow chart of the MMPS algorithm of an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application will be further described in detail below with reference to the accompanying drawings and embodiments.

[0058] In the description of this application, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise expressly defined. Terms such as "installed", "connected", "connected", and "fixed" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0059] In the description of the present application, it should be understood that the directions or positional relationships indicated by the terms "up", "down", "left", "right", "front", "back", etc. are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific orientation, and therefore, should not be understood as a limitation on the present application.

[0060] In the description of this specification, the description of the terms "one embodiment / method", "some embodiments / methods", "specific embodiments / methods", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments / methods or examples in a suitable manner.

[0061] As the instruction manual Figure 1 The purpose of the present invention is to provide a method for predicting irreversible losses of a fuel cell centrifugal air compressor, comprising:

[0062] Step 1: Based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, the performance data of the air compressor is collected under different boundary parameters, and combined with the three-dimensional geometric model of the centrifugal air compressor, a multi-physics field coupled computational fluid dynamics (CFD) simulation model of the fuel cell centrifugal air compressor is established; the convergence and accuracy of the established CFD simulation model are verified.

[0063] The purpose of step 1 is to construct a simulation model with high precision and high reliability through the performance data and three-dimensional geometric models under multiple boundary parameters collected by the test platform, aiming to provide accurate theoretical support and optimization basis for the flow characteristics analysis, thermal management optimization and performance improvement of the centrifugal air compressor, thereby reducing the test cost, improving the design efficiency, and ensuring the efficient and stable operation of the centrifugal air compressor in the fuel cell system.

[0064] Step 1 includes:

[0065] Step 1.1: Build a comprehensive performance test platform for fuel cell centrifugal air compressors, test the performance parameters, operating parameters and control parameters of the centrifugal air compressors in the full operating range, and obtain test data of the air compressors under different operating conditions.

[0066] It should be noted that the full operating range includes but is not limited to operating conditions with different intake flow rates, intake pressures, outlet pressures, air temperatures, motor speeds, and dynamic load changes; by adjusting the boundary conditions of the test platform, the key performance data of the air compressor under rated conditions, partial load conditions, overload conditions, and dynamic response conditions are collected. The collected data include but are not limited to intake pressure, intake temperature, outlet pressure, outlet temperature, air flow, motor speed, and energy consumption, etc., providing comprehensive and reliable basic data support for subsequent model establishment and optimization.

[0067] As the instruction manual Figure 2The comprehensive performance test platform of fuel cell centrifugal air compressor includes air compressor and its motor, air circuit system, water cooling system, power supply and control system.

[0068] Among them, the air circuit system is the core part of the test platform, which is used to guide air through the air compressor and measure relevant performance parameters, including air filter, intake valve, intercooler and exhaust valve. The air filter is used to filter particulate matter in the air and protect the air compressor. The intake valve is used to control the gas flow entering the air compressor. The intercooler is used to reduce the temperature of the air compressed by the air compressor. The exhaust valve is used to control the output of compressed air. The air filter is connected to the air inlet of the air compressor through the intake valve and pipeline. The air inlet of the air compressor is equipped with a pressure sensor (PT) and a temperature sensor (THA) to monitor the pressure and temperature of the input air. The air compressor compresses air under the drive of the motor, and its outlet is connected to the air inlet of the intercooler through a pipeline. The air outlet of the air compressor is equipped with a pressure sensor (PT) and a temperature sensor (THA) to monitor the outlet parameters of the compressed air. The outlet of the intercooler is connected to the exhaust pipe through the exhaust valve and pipeline, and is equipped with a temperature sensor (THA) and a flow sensor (FS) to monitor the cooling effect.

[0069] The water cooling system is used to maintain the thermal management performance of the air compressor and intercooler. It dissipates heat through circulating water and includes a water tank, a water pump, a cooling water flow path, and multiple sensors. The cooling water is stored in the water tank, and the water pump is connected to the water tank to provide a circulating water flow. The water pump is connected to the intercooler and the inlet of the air compressor cooling circuit through a pipeline. The cooling water enters the intercooler through the pipeline, taking away the heat in the compressed air. The water flowing out of the intercooler flows back to the water tank through the pipeline to form a closed loop. The multiple sensors in the water system include a flow sensor (FS) for measuring the cooling water flow, a pressure sensor (PT) for monitoring the water circuit pressure, and a temperature sensor for monitoring the temperature of the cooling water.

[0070] The power supply and control system is used to drive the air compressor and collect data, including DC power supply module, controller and sensor. The DC power supply module (high voltage power supply: Q-100V adjustable power supply and low voltage power supply: 12V power supply) is connected to the motor of the air compressor through the control line, where the Q-100V adjustable power supply is used to drive the main motor of the air compressor, and the 12V power supply is used to power auxiliary equipment such as sensors and controllers. The controller is directly connected to all sensors and actuators to monitor the inlet and outlet pressure, flow, temperature data, and to adjust the motor speed, intake valve opening and exhaust valve opening in real time.

[0071] The fuel cell centrifugal air compressor comprehensive performance test platform is used to test and record the operating performance of the air compressor under different boundary parameter conditions. During the test, by adjusting multiple variables in the platform (such as gas flow, inlet and outlet pressure, temperature, and motor speed), a comprehensive evaluation of the air compressor performance is achieved. The specific test process is as follows:

[0072] Test preparation: First, start the low-voltage power supply (12V) to power the controller and sensor, and check the connection and reading of the sensor. Start the high-voltage power supply (Q-100V), power the main motor of the air compressor and check its operating status. Then, according to the test objectives, set the boundary conditions within the test range. The boundary conditions include air flow, inlet and outlet pressures, and air temperature. The air flow is controlled by adjusting the opening of the intake valve, the inlet and outlet pressures are set by adjusting the opening of the intake and exhaust valves, and the air temperature is achieved by adjusting the test environment or the cooling capacity of the intercooler.

[0073] Test steps: Test the performance parameters of the air compressor in the initial state, including inlet and outlet pressures, temperatures and air flow, and record relevant data. The initial state is to run the air compressor under the specified initial parameters (such as standard atmospheric pressure, room temperature and rated speed). Flow change test: Adjust the opening of the intake valve, set multiple flow values ​​(such as 20%, 50%, 80% rated flow), and run the air compressor. Record the inlet pressure (PT), temperature (THA), outlet pressure (PT), outlet temperature (THA) and flow (FS) at each flow value. Pressure change test: Adjust the opening of the exhaust valve, change the outlet pressure, and test the performance under different pressure ratio conditions. Record the inlet and outlet pressure (PT), temperature (THA), flow (FS) and cooling effect of the intercooler under the corresponding conditions. Temperature change test: Adjust the environment or intercooler, set the intake temperature (such as -10℃, 25℃, 50℃), and run the test. Record the compressed air outlet temperature (THA), pressure (PT) and flow (FS) at different intake temperatures. Speed ​​change test: adjust the speed of the air compressor main motor (such as low speed 50%, rated speed 100%, high speed 120%), and run the air compressor separately. Record the inlet and outlet pressure (PT), temperature (THA) and flow (FS) at the corresponding speed. Boundary condition test: set super-design conditions, such as high flow, extremely high / low inlet temperature or super-design pressure ratio conditions, and run the air compressor. Record the operating data under extreme conditions, and pay attention to performance changes and equipment operation stability.

[0074] The data collected and recorded by the controller in real time include the pressure (PT), temperature (THA) and flow (FS) of the air inlet, the pressure (PT), temperature (THA) and flow (FS) of the air outlet, the motor speed and its energy consumption data, and the cooling water temperature (THA) and flow (FS) of the intercooler inlet and outlet. Based on the collected data, performance curves are drawn, such as the flow-pressure characteristic curve and the flow-temperature rise curve, to analyze the efficiency, cooling effect and dynamic response capability of the air compressor under different working conditions.

[0075] Step 1.2: Use 3D modeling software to construct a 3D geometric model of the centrifugal air compressor.

[0076] It should be noted that the geometric model of the centrifugal air compressor created in step 1.2 is the same as the geometric structure of the centrifugal air compressor used in the fuel cell air compressor comprehensive performance test platform test in step 1.1.

[0077] As the instruction manual Figure 3 , Figure 3 It is a component of the 3D model of the fuel cell air compressor. Specifically, first obtain the core design data of the centrifugal air compressor, including parameters such as impeller diameter, number of blades, blade curvature, diffuser structure, and volute geometry. Confirm the size and relative position of boundary conditions such as the air inlet, outlet, and cooling structure of the air compressor.

[0078] Then select 3D modeling software suitable for modeling complex fluid equipment (such as CATIA, SolidWorks or Creo), initialize the modeling environment, set the unit system, coordinate system and default precision to ensure the accuracy and consistency of the model.

[0079] Model the impeller, diffuser and other components of the centrifugal air compressor. Create an impeller model based on the design parameters, including the spatial distribution, curvature, thickness and blade spacing of the blades. Generate an axial channel at the center of the impeller and ensure that the coupling part between the impeller and the main shaft meets the design requirements. Construct the flow channel geometry of the diffuser, including the cross-sectional dimensions of the inlet and outlet, the channel curvature and the diffusion angle, and seamlessly connect the diffuser and the impeller outlet to ensure smooth gas flow. Construct a geometric model of the volute. The volute design must accurately reflect the boundary conditions of the inlet, outlet and intercooler connection to ensure structural integrity. Assemble the constructed impeller, diffuser, volute and other components, and use constraints to calibrate the position and angle of each component. Refine the mesh of key areas (such as blade edges and diffuser flow channels) to ensure accurate model details for subsequent simulation analysis. Finally, export the 3D geometric model to a file format that supports CFD analysis (such as STEP, IGES or Parasolid).

[0080] Step 1.3: Based on the test data measured in step 1.1 and the three-dimensional geometric model constructed in step 1.2, a multi-physics field coupling calculation CFD simulation model for the fuel cell centrifugal air compressor is established. The key performance parameters are calculated multiple times through the CFD simulation model to complete the convergence verification of the simulation results. The simulation calculation results are compared and analyzed with the test data obtained in step 1.1 to verify the convergence and accuracy of the CFD simulation model.

[0081] It should be noted that the simulation model comprehensively considers gas flow, heat conduction and dynamic interaction to accurately simulate the flow characteristics, temperature field distribution and performance parameters of centrifugal air compressors under different working conditions. Key performance parameters include flow, pressure, temperature and efficiency. Verifying the accuracy and reliability of the CFD simulation model can meet the needs of air compressor performance optimization and design improvement.

[0082] Specifically, first use CFD simulation software (such as ANSYS Fluent, OpenFOAM, etc.) to import the three-dimensional geometric model, and set the calculation domain and boundary conditions. Based on the test data obtained from the test platform (including inlet and outlet pressure, temperature, flow, etc.), define the boundary parameters of the simulation model. Considering the interaction of multiple physical fields, coupling the gas flow equation (NS equation), energy conservation equation and rotating machinery dynamics equation, a coupled fluid dynamics model is established.

[0083] Then the three-dimensional model of the centrifugal air compressor is meshed, and the mesh is refined in key areas (such as the impeller, diffuser flow channel and boundary layer) by combining structured meshes with unstructured meshes. Through mesh independence verification, the appropriate mesh size is selected to ensure a balance between calculation accuracy and calculation efficiency.

[0084] Convergence verification: Run CFD simulation by setting different initial conditions and iteration steps, and observe the curves of residuals (such as residuals of flow, pressure, and temperature) changing with the number of iterations. Determine whether the simulation model has reached the convergence standard. The convergence standard can be based on the following indicators: all residual values ​​drop by at least 3 orders of magnitude (such as from 10^-3 to 10^-6); global physical quantities (such as inlet and outlet flow, pressure, and temperature) are stable and the change range is lower than the set threshold (such as lower than 0.1%). Compare the simulation results of different grid densities and time steps to verify the stability and consistency of the calculation results.

[0085] Verify accuracy: Select multiple typical operating conditions (such as rated speed, partial load, overload conditions, etc.), run CFD simulation, and record key performance parameters, including flow, pressure, temperature, efficiency, etc. Compare and analyze the simulation results with the test data measured by the test platform, and calculate the error index (such as absolute error, relative error or root mean square error): If the error range of key parameters is controlled within the allowable range (such as within 5%), the simulation model is considered to have high accuracy. Analyze the source of the error and determine whether it is necessary to adjust the model assumptions, boundary conditions or optimize the meshing.

[0086] Finally, for working conditions where there are deviations between the test data and the simulation results, adjust the model parameters (such as turbulence model, boundary conditions) or increase the simulation complexity (such as considering the unsteady turbulence model). Re-verify the convergence and accuracy of the model until the simulation results fully match the test data. Through the above process, the convergence and accuracy verification of the CFD simulation model is completed to ensure that it can accurately reflect the flow characteristics, thermodynamic properties and efficiency characteristics of the centrifugal air compressor under various boundary conditions. The simulation model finally verified provides a reliable theoretical basis and technical support for the performance optimization and design improvement of centrifugal air compressors.

[0087] Step 2: Define N types of irreversible losses for different components of the air compressor, and determine M structural parameters related to the irreversible losses based on the structural characteristics of each component. Construct an integrated CFD simulation framework based on the CFD simulation model of the fuel cell air compressor. Determine the number of levels and parameter combinations of the M structural parameters by designing orthogonal experiments, generate a parameter combination table, and import the parameter combination table into the CFD simulation framework. Use the CFD simulation framework to perform simulation calculations on all parameter combinations in the parameter combination table in turn, and extract key data corresponding to each type of irreversible loss from each set of simulation results.

[0088] The purpose of step 2 is to systematically extract various types of irreversible losses (such as flow loss, thermodynamic loss, etc.) of different components of the air compressor under multiple structural parameter combinations by building a CFD integrated simulation framework for fuel cell air compressors, combining orthogonal experimental design and automatic batch simulation methods, quantify their influencing characteristics and establish the correlation between losses and structural parameters. Through efficient data generation and preprocessing, a comprehensive and reliable data foundation is provided for the development of subsequent performance optimization models, thereby supporting the optimal design and performance improvement of air compressors.

[0089] Step 2 includes:

[0090] Step 2.1: According to the main sources of energy loss in the operation of the air compressor, the irreversible loss types are divided into flow loss, thermodynamic loss, mechanical loss and shock wave loss. According to the influence of different components of the air compressor on the energy loss, the structural parameters that affect the irreversible loss are determined.

[0091] Specifically, flow loss refers to the kinetic energy dissipation caused by eddy currents, flow separation and secondary flow. Thermodynamic loss refers to the heat energy dissipation caused by the entropy increase effect during compression. Mechanical loss refers to the friction loss between bearings, seals and rotating parts. Shock wave loss refers to the rapid energy dissipation caused by shock waves generated in high-speed flow.

[0092] The key components of the air compressor include impeller, diffuser and volute. Based on the key components of the air compressor, the structural parameters that affect the irreversible loss are determined. The structural parameters of the blade that affect the irreversible loss include but are not limited to: blade inlet installation angle, blade outlet installation angle, and outlet blade thickness. Among them, the blade inlet installation angle affects flow separation and vortex generation, the blade outlet installation angle affects fluid momentum loss, and the blade outlet thickness affects turbulence intensity and flow loss. The structural parameters of the volute that affect the irreversible loss include but are not limited to: volute cross-sectional ellipticity, volute outlet diameter, and volute tongue angle. Among them, the volute cross-sectional ellipticity affects secondary flow and flow distribution, the volute outlet diameter affects the outlet velocity and shock wave loss, and the volute tongue angle affects flow stability. The structural parameters of the diffuser that affect the irreversible loss include but are not limited to: diffuser outlet radius, diffuser inlet diameter, and diffuser outlet width. Among them, the diffuser outlet radius affects the fluid pressure recovery efficiency, the diffuser inlet diameter affects the fluid contraction effect, and the diffuser outlet width affects the flow field uniformity.

[0093] Step 2.2: Import the structural parameters of each component of the air compressor that affect the irreversible loss determined in step 2.1 as input variables into the CFD simulation model, perform parameterized modeling on the structural parameters, generate CFD simulation models for multiple different working conditions, expand the CFD simulation model to meet the analysis requirements of the irreversible loss types, build a multi-physics field simulation framework based on the CFD simulation model, and define the calculation method for each irreversible loss in the multi-physics field simulation framework.

[0094] The multi-physics simulation framework based on the CFD simulation model is as shown in the attached manual. Figure 4 As shown in the figure, the multi-physics simulation framework demonstrates a complete closed-loop process from geometric modeling to performance analysis. The framework uses CFturbo (turbomachinery design software) to create a parametric geometric model of the key components of the air compressor, and imports it into ANSYS Mesh or TurboGrid for high-quality meshing; then, CFX is used to set boundary conditions and physical models to complete the CFD simulation solution of flow, thermodynamics and mechanical properties; finally, CFD-Post is used to extract data such as velocity field, temperature field, and pressure field for post-processing analysis, and the design parameters are optimized based on the simulation results to form an iterative design cycle, thereby achieving the improvement of air compressor performance and the quantitative analysis of irreversible losses.

[0095] After the introduction of irreversible loss types, the multi-physics field simulation framework includes fluid field analysis module, thermodynamic field analysis module, mechanical field analysis module and shock wave field analysis module, which are used to analyze the corresponding irreversible losses.

[0096] The flow loss is calculated by analyzing the vortex intensity and the pressure loss in the flow separation area. The flow loss is expressed by the entropy increase rate caused by viscous dissipation and turbulent dissipation. The entropy increase rate caused by viscous dissipation describes the energy dissipation of the fluid due to viscous friction (such as shear force), which mainly manifests as significant shear dissipation near the boundary layer. The entropy increase rate caused by viscous dissipation is determined by the following formula:

[0097]

[0098] Where: s v represents the entropy increase rate caused by viscous dissipation; μ represents the dynamic viscosity (reflecting the internal friction characteristics of the fluid); T represents the thermodynamic temperature of the system; τ ij represents the viscous stress tensor (describing the stress component inside the fluid); u i represents the velocity component in the i-th direction; x j represents the spatial coordinates of the jth direction; Represents the velocity gradient (reflects the rate of change of velocity in the spatial coordinate direction).

[0099] The entropy increase rate due to turbulent dissipation describes the inevitable energy dissipation of turbulent eddies during the energy classification process, and the kinetic energy loss caused by vortices or vortex streets in the turbulent flow field. The entropy increase rate due to turbulent dissipation is determined by the following formula:

[0100]

[0101] Where: s v’ represents the entropy increase rate caused by turbulent dissipation; β represents the empirical coefficient, which is used to characterize the effect of eddy dissipation on entropy increase; ρ m represents fluid density, reflecting the mass of fluid per unit volume; k represents turbulent kinetic energy, representing the kinetic energy per unit mass in turbulence; w represents turbulent frequency, reflecting the rate of energy dissipation in turbulence; T represents temperature (absolute temperature scale).

[0102] The calculation method of thermodynamic loss is to quantitatively analyze the heat energy dissipation according to the entropy increase calculation formula. Thermodynamic loss is expressed by the entropy increase rate caused by the temperature gradient. The temperature gradient reflects the irreversible thermodynamic loss caused by the temperature difference during the heat conduction process. The typical scenario includes the transfer of heat from the high temperature area to the low temperature area during the compression process. The entropy increase rate caused by the temperature gradient is determined by the following formula:

[0103]

[0104] Where: s t represents the rate of entropy increase caused by temperature gradient; T represents temperature (absolute temperature scale); k e Indicates the thermal conductivity coefficient (reflects the thermal conductivity of the fluid); represents the temperature gradient (rate of change of temperature in space); Represents the square of the temperature gradient (reflects the intensity of temperature change).

[0105] The mechanical loss is calculated by combining the bearing friction torque and speed to calculate the friction power. The mechanical loss is expressed by the entropy increase rate caused by wall friction. Wall friction reflects the loss caused by friction and heat transfer when the fluid contacts the wall. The typical scenario is the friction loss of the inner wall flow channel of the air compressor or the diffuser wall. The entropy increase rate caused by wall friction is determined by the following formula:

[0106]

[0107] Where: s w represents the entropy increase rate caused by wall friction; τ w represents the wall shear stress, which indicates the shear force of the fluid on the wall; v represents the first layer grid velocity near the wall, which reflects the flow velocity near the wall; T represents the temperature (absolute temperature scale).

[0108] The shock wave loss is calculated by locating the shock wave area through flow field analysis and calculating the loss caused by the shock wave intensity. The shock wave loss is expressed by the entropy increase rate caused by temperature fluctuations. Temperature fluctuations describe the pressure energy loss caused by shock waves in high-speed flows, such as shock wave losses in impeller flow channels or diffusers. The entropy increase rate caused by temperature fluctuations is determined by the following formula:

[0109]

[0110] Where: s t‘ represents the entropy increase rate caused by temperature pulsation; λ represents the thermal diffusivity, which describes the ability of heat diffusion; λ t Represents the reference thermal diffusivity, used for normalized calculation; s t represents the entropy increase rate caused by temperature gradient (same as formula (3)).

[0111] Furthermore, formulas (1)-(5) are the rate of increase of entropy generated by irreversible processes (viscous dissipation, heat conduction, eddy current dissipation, etc.) in a specific area per unit time. v 、s v’ 、s t 、s w 、s t‘ Integrate over the entire space to get the corresponding total entropy increase rate S' v , S' v’ , S' t , S' w , S' t‘ The corresponding total entropy increase rate can be expressed by the following formula

[0112] S'=∫sdV(6)

[0113] The total entropy increase rate reflects the comprehensive effect of irreversible energy transfer in the system (such as heat conduction, viscosity, turbulent dissipation, etc.). By analyzing each component, it can be determined which physical mechanism contributes the most to the entropy increase, thereby optimizing the system design or control method to reduce irreversible losses.

[0114] Step 2.3: Based on the M structural parameters and their levels of each air compressor component that affect irreversible losses, select the corresponding orthogonal table to generate a parameter combination table, automatically import the parameter combination into the CFD simulation model constructed in step 2.2, and perform simulation calculations on all parameter combinations in turn. For each set of simulation results, extract the velocity field, temperature field and other related data, and apply wavelet denoising to the data.

[0115] Specifically, first determine the test parameters and levels, M structural parameters, and set several levels for each parameter (such as 3 levels: small value, medium value, and large value). For example: blade inlet angle [10°, 15°, 20°], volute outlet diameter [100mm, 120mm, 140mm]. According to the number of parameters M and the number of levels L of each parameter, select a suitable orthogonal table. In the implementation method of the present application, there are 9 structural parameters that affect the irreversible loss of each component of the air compressor (blade inlet installation angle, blade outlet installation angle, outlet blade thickness, volute section ellipticity, volute outlet diameter, volute tongue angle, diffuser outlet radius, diffuser inlet diameter, and diffuser outlet width). Therefore, there are 9 structural parameters, each with 3 levels. The L27 orthogonal table (27 groups of combinations) can be selected to ensure that all parameter combinations cover the interaction of all factors as much as possible. Use tools (such as Excel, Python scripts, or professional software) to generate all parameter combinations. Then, use an automated script (such as Python, MATLAB, or Shell script) to import the parameter combination of the orthogonal table, import the geometric model of the different working condition model generated in step 2.2 into the CFD software, set the simulation conditions (such as meshing, boundary conditions), run the script, and simulate and calculate each group of parameter combinations in turn in combination with the calculation method of each irreversible loss in step 2.2, and extract the fluid mechanics field, thermodynamics field, mechanical loss, and shock wave loss from each simulation result. In the fluid mechanics field, extract the flow velocity distribution for analyzing the flow loss; extract the pressure gradient for calculating the shock wave loss. In the thermodynamic field, extract the temperature distribution for calculating the thermodynamic loss; extract the entropy increase data through the energy equation. In the mechanical loss, extract the relevant data of the wall friction loss. In the shock wave loss, extract the shock wave position and intensity data for calculating the energy dissipation. Store the extracted data in an easy-to-process format (such as CSV, SQL database), and each group of parameter combinations corresponds to a group of data, which is convenient for subsequent correlation analysis. Finally, each set of simulation data (such as velocity field and temperature field) is decomposed by wavelet, the threshold is set, the high-frequency components are processed by soft / hard threshold, the denoised data is obtained by wavelet reconstruction, and all simulation data are normalized to a unified range (such as [0,1]).

[0116] Step 3: Propose the RL-GHEM method, construct multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and punishment mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy, and construct an irreversible loss prediction model for air compressors under different working conditions.

[0117] The purpose of step 3 is to select and independently train multiple base models by proposing the RL-GHEM method (i.e., an optimization method based on reinforcement learning, RL, and hybrid ensemble model, GHEM), comprehensively capture the multidimensional characteristics of irreversible losses, and provide a reliable data basis for subsequent dynamic optimization. The weight distribution and combination strategy of the base models are adjusted in real time through the reinforcement learning controller, so that the model can adapt to real-time changing working conditions and data characteristics, thereby improving the flexibility and accuracy of the prediction.

[0118] As the instruction manual Figure 5 , showing the cyclic process of reinforcement learning in the RL-GHEM method, combining the interactive relationship between "environment" and "agent". The environment represents a base model library with different weights, which includes various trained models (such as DNN, SVM, LSTM, etc.). The agent represents the reinforcement learning controller and is the core optimization module of the entire system. The state describes the characteristic information of the current environment, including the mean square error calculated based on the current model configuration and the current weights of each base model. The reward is used to measure the effect of the action generated by the agent. It is the feedback mechanism of reinforcement learning. The reward is usually directly related to the mean square error (MSE) and reflects the quality of the model combination strategy. The action is the operation generated by the agent based on the current state, which is used to optimize the weights and combination strategies of the base models. The action directly acts on the environment and updates the base model configuration.

[0119] Step 3 specifically includes:

[0120] Step 3.1: Select multiple types of base models, build a base model library, divide the irreversible loss data into training subsets and test subsets, perform independent training on each base model on its corresponding training subset, evaluate the performance of each base model on the test subset, calculate the corresponding mean square error, and assign initial weights through the reinforcement learning mechanism based on the evaluation results to complete the initialization of the base model library.

[0121] Specifically, first select multiple types of base models to build a model library. The base models include but are not limited to deep neural networks (DNN), support vector machines (SVM), classification regression decision trees (CART), long short-term memory networks (LSTM), etc. Deep neural networks (DNN) are used to process complex nonlinear features and high-dimensional data. Support vector machines (SVM) are good at modeling small sample data and capturing boundary features in high-dimensional space. Classification regression decision trees (CART) are suitable for processing nonlinear and discrete features. Long short-term memory networks (LSTM) focus on capturing the timing characteristics and dynamic changes of data. According to the characteristics of irreversible loss data (such as time series, nonlinear trends, etc.), select appropriate data feature processing methods. According to the characteristics of different base models, preset specific hyperparameters (such as the number of hidden layers of deep neural networks, the type of kernel functions of support vector machines, and the time step of LSTM).

[0122] Then, an independent training and testing environment is set up for each base model to ensure that each base model in the model library performs well in specific tasks and covers different modeling advantages. The irreversible loss data includes irreversible loss data of fuel cell air compressors under different working conditions (such as flow loss, thermodynamic loss, etc.). The irreversible loss data is divided into training subsets and test subsets according to a certain ratio (such as 80% training set, 20% test set), ensuring that the data distribution of the training subset and the test subset is consistent to avoid affecting the model performance due to data distribution differences. Each base model is trained independently on its own training subset to avoid interference between models. Each base model is trained independently on its own training subset to avoid interference between models. The hyperparameters of the model are optimized by cross-validation method to ensure the generalization ability of each base model. The performance of each base model is evaluated on the test subset, and its mean square error (MSE) is calculated as the main indicator. For each base model, its prediction ability under different working conditions is tested one by one, and the performance of the model on various types of irreversible losses is compared.

[0123] Finally, according to the mean square error (MSE) calculated on the test subset, the initial weight is assigned according to the MSE, and the reinforcement learning mechanism is used to assign initial weights to each base model, providing a basis for subsequent dynamic optimization. Weight allocation principle: the better the performance (the smaller the MSE), the higher the initial weight; the model with poor performance is assigned a lower weight.

[0124] Step 3.2: Initialize the reinforcement learning controller, set the controller parameters including state information, action set and reward function, receive the state information of the current base model, and the controller generates actions based on the state information. The actions include adjusting the base model weights or changing the model combination strategy; calculate the reward signal based on the overall model prediction performance, and optimize the controller strategy through the reinforcement learning algorithm.

[0125] Specifically, deep reinforcement learning (such as Q-learning or policy gradient method) is first adopted, and the controller is designed as an intelligent agent that can learn and optimize in the state-action-reward cycle. The state information of the controller input includes the prediction mean square error (MSE), weight distribution and historical performance of the base model. The prediction mean square error (MSE) of the base model is used to evaluate the current prediction performance of the base model, the weight distribution is used to evaluate the current importance of the base model in the integrated model, and the historical performance is used to record the performance trend of the base model in multiple rounds of training and testing. The actions generated by the controller include adjusting the weights of the base model and changing the combination strategy of the base model (such as switching linear weighted or nonlinear weighted combination methods).

[0126] Then set the set of actions that the controller can take, which includes adjusting the weights of the base models, changing the combination strategy, retraining specific base models, and introducing new base models. Adjusting the weights of the base models means increasing or decreasing the weight of a base model. Changing the combination strategy means switching between linear weighted average and nonlinear weighted combination. Retraining a specific base model means retraining the base model when the performance is low. Introducing a new base model means introducing a new base model when the existing model library cannot meet the performance requirements.

[0127] Furthermore, a reward function is defined to evaluate the effect of the controller's actions and provide feedback for the next decision. The design goal of the reward value is to improve the overall prediction accuracy and system stability. The reward function includes the overall prediction error, weight distribution efficiency, and action complexity penalty.

[0128] The overall prediction error can be expressed as:

[0129] R1=-MSE total (7)

[0130] Where: MSE total Represents the overall prediction mean square error of the hybrid ensemble model.

[0131] The weight distribution efficiency can be expressed as:

[0132]

[0133] The action complexity penalty can be expressed as:

[0134]

[0135] Where: C a Indicates the complexity of the actions taken by the controller (such as the penalty value for frequently adjusting weights).

[0136] According to formulas (7)-(9), we get the reward function:

[0137] R=R1+αR2+βP(10)

[0138] Where: α and β represent adjustment coefficients, balancing prediction accuracy and computational complexity.

[0139] The above is the process of initializing the reinforcement learning controller. Then the current base model state information and the state information of the aggregated integrated model are collected and passed to the controller using a vectorized representation method. The current base model state information includes the latest prediction error (MSE) of each base model, the current weight distribution of the extracted base model, the historical performance of the extracted base model, and the analysis of its performance trend. The state information of the aggregated integrated model includes the total prediction error of the aggregated integrated model (such as the overall MSE) and the recording of the current combination strategy (such as linear weighting or nonlinear weighting). Use a vectorized representation method to pass the state information to the controller:

[0140] S=[MSE1,MSE2,……,MSE N ,w1,w2,……,w N ,Strategy](11)

[0141] Where: N represents the number of base models; w i represents the weight of the i-th base model.

[0142] After the state information is input into the controller, the controller selects the optimal action A through the reinforcement learning algorithm according to the current state information S. Action A includes adjusting the weight of a certain model, changing the combination strategy, etc. In the initial stage, more action combinations are explored through random sampling, and the optimal action is selected through strategy optimization in the later stage. After selecting the optimal action, adjust the weight of the base model or the combination strategy. Adjust the update weight, and i Based on the implementation of w i +Δw, Δw represents the weight adjustment value calculated by the controller. Switching combination strategy, for example: when the action is A1, the switching combination strategy is linear weighting; when the action is A2, the switching combination strategy is nonlinear weighting.

[0143] Furthermore, since the controller adjusts the parameters (such as weights or strategies) of the hybrid ensemble model after generating an action, which is reflected in the prediction performance of the hybrid ensemble model, the reward signal is updated according to the prediction performance of the hybrid ensemble model. First, the reward signal is calculated according to the overall prediction performance of the adjusted model according to formula (10), and the reward value is generated by comparing the total prediction error and the rationality of the weight distribution before and after the adjustment. Then the reward signal is used to optimize the controller's strategy and update the Q value in Q-learning. η represents the learning rate and γ represents the discount factor. Optimize the policy parameters in the policy gradient method: Among them, J(θ) represents the policy objective function.

[0144] By initializing the reinforcement learning controller, setting the state information, action set and reward function, dynamically inputting the current model state, generating actions for weight adjustment or strategy change, and using reward signals to optimize the controller strategy, the prediction performance and adaptability of the hybrid integrated model can be gradually improved.

[0145] Step 3.3: Monitor the performance of the base models in real time, record the mean square error, computational complexity and generalization ability, adjust the weights of the base models based on the reward mechanism, optimize the overall model performance by increasing the weights of the base models with good performance or reducing the weights of the base models with poor performance, and dynamically select the model combination method according to the real-time data characteristics. The model combination methods include linear weighted average and nonlinear weighted combination. Apply the updated weight distribution and combination strategy to the hybrid integration model to complete the dynamic adjustment.

[0146] Specifically, the prediction mean square error (MSE), computational complexity, generalization ability and stability of each base model are first monitored. After each prediction, the above indicators are recorded and updated to the state information of the reinforcement learning controller. The prediction mean square error (MSE) is the error of the base model on the test set, reflecting its prediction accuracy. Computational complexity is a measure of the running time and resource consumption of the base model to avoid high-complexity models occupying too much weight. Generalization ability is to evaluate the ability of the base model to cope with new data through cross-validation or new data testing. Stability is to observe the performance fluctuations of the base model under different working conditions and real-time data characteristics.

[0147] Then increase the weight of the base model with good performance (low MSE, strong generalization ability, and high stability). The specific formula is:

[0148]

[0149] In the formula: α represents the learning rate; Reward i Represents the reward value.

[0150] Reduce the weight of the base model with poor performance (high MSE, high complexity, poor stability), formula:

[0151]

[0152] Where: β represents the learning rate; Penalty i Indicates the penalty value.

[0153] Make sure the adjusted weights meet the normalization condition:

[0154]

[0155] Furthermore, the optimal model combination strategy is dynamically selected based on the real-time data characteristics. When the data characteristics are simple or the working conditions are stable, a linear weighted combination is used:

[0156]

[0157] Where: w i represents the basis model weight; y i Represents the base model output.

[0158] When the data features are complex or the working conditions are changeable, a nonlinear combination strategy (such as power average) is used:

[0159]

[0160] Where: p represents the adjustment index, which determines the degree of nonlinearity.

[0161] After each prediction, the adjusted weights and combined strategies are updated to the hybrid ensemble model according to the actions of the reinforcement learning controller (weight adjustment and strategy switching). The new prediction performance is fed back to the reinforcement learning controller to update its state information to optimize the next round of decision-making.

[0162] Step 3.4: Set the trade-off strategy between exploration and utilization behavior to determine whether the current state is to perform exploration behavior or utilization behavior. In the exploration phase, expand the search space by randomly perturbing the base model weights or introducing new model combination strategies. In the utilization phase, optimize the overall prediction performance by selecting the current best performing model combination strategy. Dynamically adjust the ratio of exploration and utilization based on historical reward feedback to achieve continuous optimization of the base model configuration and performance improvement.

[0163] Specifically, the exploration and utilization mechanisms are defined. The exploration mechanism is that the controller randomly adjusts the weights of the base models, tries new model combinations, or introduces new base models to expand the search space. The utilization mechanism is that the controller selects the best performing model combination and weight distribution based on the current historical feedback to optimize the current prediction performance. In the initial stage, exploration is prioritized, and a higher exploration probability is set to obtain a comprehensive understanding of the characteristics of the irreversible loss model. As the optimization process progresses, the exploration probability is gradually reduced, the utilization ratio is increased, and the stability of the system performance is improved. A dynamic adjustment formula based on time steps is adopted:

[0164]

[0165] Where: P 探索 represents the probability of exploration; t represents the current iteration number; t c represents the equilibrium point, which determines the speed of switching from exploration to exploitation; τ represents the adjustment rate, which controls the slope of exploration decline.

[0166] Furthermore, in the exploration phase, the search space is expanded and random perturbations are introduced to the existing base model weights:

[0167] w' i =wi +η·rand(-1,1) (18)

[0168] Where: w' i represents the new weight after perturbation; w i represents the current weight; η represents the disturbance amplitude, set a small value to avoid drastic fluctuations; rand(-1,1) represents the random number generator.

[0169] Then, unused base models are randomly selected to be added to the current combination, and new weighting strategies (such as nonlinear weighted combination, power weighted average) are adopted for the existing combination. The performance of each explored model configuration is evaluated (mean square error, computational complexity, etc.), and the results are stored in the experience pool for subsequent reference.

[0170] In the utilization phase, the current model performance is optimized, and the optimal model combination strategy is extracted from the experience pool based on the historical reward function or the current model configuration performance. The weighted update rule is adopted:

[0171]

[0172] Where: represents the updated weight; w i Indicates the current weight; represents the optimal weight; α represents the smoothing coefficient, which controls the update speed.

[0173] Based on the current optimal configuration, small-scale perturbations are made to fine-tune the weights to ensure the local optimality of the model combination strategy.

[0174] Furthermore, based on historical rewards, the ratio of exploration and utilization is dynamically adjusted. By analyzing the changing trend of the reward function over time, the ratio of exploration and utilization is dynamically adjusted: when the reward value grows slowly or stagnates, the exploration ratio is increased to jump out of the local optimum; when the reward value increases rapidly, the utilization ratio is increased to consolidate the current optimal strategy. Reward function form:

[0175] R=-MSE+λ·S(20)

[0176] Where: MSE represents the mean square error of model prediction; S represents the model stability index (such as the degree of fluctuation of weight changes); λ represents the stability weight factor.

[0177] The present invention realizes the accurate prediction and dynamic optimization of multi-dimensional parameters by constructing a fuel cell centrifugal air compressor test bench and a CFD simulation model, and combining reinforcement learning with the RL-GHEM method of a hybrid integrated model, thus providing efficient and intelligent data support and optimization path for the energy loss management and performance improvement of the air compressor.

[0178] Example

[0179] The method based on the present invention optimizes the performance of the fuel cell centrifugal air compressor.

[0180] Step 1: Build a comprehensive performance test platform for fuel cell centrifugal air compressors for multi-condition performance data collection. The platform includes: Air compressor: impeller diameter 150mm, maximum speed 60,000rpm. Air circuit system: including air filter, intake valve, intercooler and exhaust valve. Water cooling system: used for thermal management, equipped with circulating water pump and cooling sensor. Power supply and control system: including Q-100V adjustable DC power supply to drive the main motor of the air compressor, and 12V power supply to power the controller and sensor. Set a pressure sensor (PT) and temperature sensor (THA) at the air inlet, a pressure sensor (PT), a temperature sensor (THA) and a flow sensor (FS) at the air outlet, and a flow sensor (FS) and a temperature sensor in the cooling water circuit.

[0181] Set up the following test conditions:

[0182] Rated operating conditions: inlet pressure 100kPa, flow rate 50g / s, outlet pressure 200kPa.

[0183] Partial load: inlet pressure 90kPa, flow rate 30g / s, outlet pressure 150kPa.

[0184] High load: inlet pressure 110kPa, flow rate 70g / s, outlet pressure 250kPa.

[0185] Dynamic conditions: simulate rapid pressure surges and flow changes.

[0186] Then start the test platform and record data under each working condition, including pressure (PT), temperature (THA), flow (FS) at the inlet and outlet, as well as motor speed and energy consumption. By adjusting the opening of the inlet and exhaust valves, the pressure ratio and flow rate are dynamically adjusted, and performance curve data such as flow-pressure curve and temperature rise curve are collected.

[0187] According to the actual structural parameters of the air compressor on the test platform: Impeller: number of blades 10, blade outlet angle 30°, diameter 150mm. Diffuser: flow channel curvature radius 50mm, outlet width 10mm. Volute: inlet diameter 40mm, outlet diameter 60mm. SolidWorks software was used to generate a three-dimensional geometric model, and the structures of the impeller, diffuser and volute were parametrically designed to ensure geometric consistency with the test platform. The model was exported in STEP format for CFD analysis.

[0188] Import the 3D geometry model into ANSYS Fluent. Set the computational domain and boundary conditions: the inlet and outlet pressures and temperatures are based on test data, the fluid is air, and the turbulence model (k-ε model) is adopted. Use a division method that combines structured and unstructured grids, with a high density of grid cells in the impeller area, a refined grid of 800,000 cells, and moderately refined diffuser and volute areas, totaling 2 million cells. Verify the grid independence of key areas (such as blade edges) and select an appropriate grid size.

[0189] Then run the simulation, iterate 1000 steps, monitor the convergence residuals: pressure and temperature residuals <10^-6. Compare the simulation results with the test data: Rated working condition: simulation flow 50.5g / s (error 1%), outlet pressure 198kPa (error 1%). High load working condition: simulation flow 71g / s (error 1.5%), outlet pressure 245kPa (error 2%). The results show that the simulation model has good accuracy and convergence.

[0190] Extract key performance data from the simulation results: Flow field: Observe the vortex distribution at the impeller outlet and find that there is obvious flow separation in the high-speed area. Temperature field: A temperature rise area appears at the diffuser flow channel outlet, indicating significant thermodynamic losses. Pressure field: The pressure distribution at the volute outlet is uneven, indicating the possibility of shock wave losses.

[0191] Step 2: Based on the three-dimensional CFD simulation model and experimental data established in step 1, classify the irreversible losses in the operation of the air compressor and determine the structural parameters related to the irreversible losses. Impeller: The blade inlet angle (10°~20°) affects the flow separation, the blade outlet angle (30°~50°) affects the fluid momentum loss, and the blade thickness (2mm~5mm) affects the turbulence intensity. Diffuser: The outlet radius (50mm~70mm) affects the pressure recovery efficiency, the inlet diameter (40mm~60mm) affects the fluid contraction effect, and the outlet width (10mm~20mm) affects the flow field uniformity. Volute: The cross-sectional ellipticity (0.8~1.2) affects the secondary flow, the outlet diameter (100mm~140mm) affects the shock wave loss, and the volute tongue angle (10°~30°) affects the flow stability.

[0192] CFturbo software was used to generate parametric geometric models for the impeller, diffuser, and volute. Different levels of values ​​were set for each parameter, such as the blade inlet angle [10°, 15°, 20°] and the volute cross-section ellipticity [0.8, 1.0, 1.2]. The output geometric model was imported into ANSYS Mesh and high-quality meshing was used. A structured mesh of 1 million units was used in the impeller area, and a total of 1.5 million units were used in the diffuser and volute areas, and the boundary layer was meshed.

[0193] A multi-physics field simulation framework was constructed through the fluid field analysis module, thermodynamic field analysis module, mechanical field analysis module, and shock wave field analysis module, and the simulation results of the flow field, temperature field, and pressure field under different parameter combinations were compared with the experimental data of step 1. The results showed that the flow, temperature, and pressure errors of the simulation model were all within 3%, verifying the reliability of the model.

[0194] Then, based on the 9 structural parameters and the 3 levels of each parameter, the L27 orthogonal table (27 groups of parameter combinations) was selected, and the parameter combination table was generated using a Python script and automatically imported into the CFD simulation framework. For each group of parameter combinations, the CFD simulation was run. Each group of simulation calculations took about 3 hours to complete all 27 groups of simulations. The 27 groups of simulation results include fluid mechanics field data (such as flow velocity distribution, pressure gradient), thermodynamic field data (such as temperature distribution, entropy increase rate), mechanical loss related data (such as wall friction shear force), shock wave loss related data (such as shock wave intensity and range). Wavelet denoising was used to denoise the simulation data (such as flow velocity, temperature) and extract key features. All simulation data were normalized to [0,1] and stored as CSV files for subsequent analysis.

[0195] Determine the structural parameters and optimization directions that have the greatest impact on losses: blade inlet angle 15°: reduce flow separation and increase flow by 5%. Diffuser outlet width 15mm: reduce entropy increase rate by 15%. Volute outlet diameter 120mm: reduce shock wave loss by 10%.

[0196] Step 3: Select a variety of models suitable for irreversible loss data characteristics: deep neural network, support vector machine, classification regression decision tree, long short-term memory network, and build a base model library. Based on the test data collected in step 1 and the orthogonal test simulation data in step 2, build a training set and a test set (80% training set, 20% test set). Data features include: flow loss related features (eddy current intensity, flow velocity distribution), thermodynamic loss related features (temperature gradient, entropy increase rate), mechanical loss related features (wall friction coefficient, shear force), shock wave loss related features (pressure gradient and intensity in the shock wave area).

[0197] Train each base model independently. For the deep neural network, set the number of hidden layers to 4 and the activation function to ReLU. For the S support vector machine, use the radial basis kernel function and optimize the C parameter and the γ parameter. For the classification and regression decision tree, limit the maximum depth to 10 to prevent overfitting. For the long short-term memory network, set the time step to 10 and the hidden unit to 64. Evaluate the mean square error (MSE) of each base model on the test set, which is 0.008 for the deep neural network, 0.015 for the support vector machine, 0.02 for the classification and regression decision tree, and 0.007 for the long short-term memory network. According to the MSE results of the test set, the initial weights are assigned to the base models through the reinforcement learning mechanism, with a weight of 0.3 for the deep neural network, 0.2 for the support vector machine, 0.1 for the classification and regression decision tree, and 0.4 for the long short-term memory network. The trained deep neural network, support vector machine, classification and regression decision tree, and long short-term memory network models are obtained.

[0198] A reinforcement learning controller is designed, and deep Q learning (DQN) is used to optimize the controller strategy. In the initial stage, a variety of weight allocation combinations are tried through random exploration (ε-greedy strategy). Later, the weight allocation and combination strategy are optimized based on the policy gradient method.

[0199] After each prediction, record the MSE, computational complexity, and generalization ability of the base model. Increase the weight of the base model with excellent performance (low MSE and strong generalization ability), and reduce the weight of the base model with poor performance (high MSE and high computational complexity). When the real-time data features change little, a linear weighted combination strategy is adopted. When the real-time data features are complex or change dramatically, switch to a nonlinear combination strategy. Then randomly adjust the base model weights or try new combination strategies, and select the current optimal combination strategy and weight distribution based on historical rewards. In the early stages, set a higher exploration probability (ε=0.5) to expand the search space. As training progresses, gradually reduce the exploration probability (ε=0.1), increase utilization behavior, and ensure system stability.

[0200] Under dynamic conditions (flow fluctuation of 20%, pressure change of 15%), the optimized hybrid integrated model reduces the total prediction error (MSE) by 30% and improves the computational efficiency by 25%. Compared with the fixed weight model, the RL-GHEM model significantly improves the prediction accuracy and robustness under different conditions.

[0201] Another object of the present invention is to provide a fuel cell centrifugal air compressor irreversible loss prediction system, comprising:

[0202] The data acquisition and model building module is used to collect the performance data of the air compressor under different boundary parameters based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, and to establish a multi-physical field coupling calculation CFD simulation model of the fuel cell centrifugal air compressor in combination with the three-dimensional geometric model of the centrifugal air compressor, and to verify the convergence and accuracy of the CFD simulation model.

[0203] The parameter optimization and key data extraction module is used to define N types of irreversible losses for different components of the air compressor, and determine M structural parameters related to the irreversible losses based on the structural characteristics of each component. Based on the CFD simulation model of the fuel cell air compressor, an integrated CFD simulation framework is constructed. By designing orthogonal experiments, the number of levels and parameter combinations of the M structural parameters are determined, a parameter combination table is generated, and the parameter combination table is imported into the CFD simulation framework. Using the CFD simulation framework, simulation calculations are performed on all parameter combinations in the parameter combination table in turn, and key data corresponding to each type of irreversible loss are extracted from each group of simulation results.

[0204] The prediction model construction module is used to propose the RL-GHEM method, build multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and penalty mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, and dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy to construct an irreversible loss prediction model for air compressors under different working conditions.

[0205] The above is only an embodiment of the present invention, and the common sense such as the known specific structure and characteristics in the scheme is not described in detail here. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the attached claims rather than the above description, so it is intended to include all changes within the meaning and scope of the equivalent elements of the claims. Any figure mark in the claims should not be regarded as limiting the claims involved.

Claims

1. A method for predicting irreversible losses of a fuel cell centrifugal air compressor, characterized in that: Methods include: Step 1: Based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, the performance data of the air compressor is collected under different boundary parameters, and combined with the three-dimensional geometric model of the centrifugal air compressor, a multi-physics field coupling calculation CFD simulation model of the fuel cell centrifugal air compressor is established; the convergence and accuracy of the established CFD simulation model are verified; Step 2: Define N types of irreversible loss for different parts of the air compressor, and determine M structural parameters related to the irreversible loss based on the structural characteristics of each part. Based on the CFD simulation model of the fuel cell air compressor, build an integrated CFD simulation framework, determine the number of levels and parameter combinations of the M structural parameters by designing orthogonal experiments, generate a parameter combination table, and import the parameter combination table into the CFD simulation framework. Use the CFD simulation framework to perform simulation calculations on all parameter combinations in the parameter combination table in turn, and extract key data corresponding to each type of irreversible loss from each set of simulation results; Step 3: Propose the RL-GHEM method, construct multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and punishment mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy, and construct an irreversible loss prediction model for air compressors under different working conditions.

2. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 1, characterized in that: Step 2 includes: Step 2.1: According to the main sources of energy loss in the operation of the air compressor, the irreversible loss types are divided into flow loss, thermodynamic loss, mechanical loss and shock wave loss. According to the influence of different components of the air compressor on the energy loss, the structural parameters that affect the irreversible loss are determined; Step 2.2: Import the structural parameters of each air compressor component that affects the irreversible loss determined in step 2.1 as input variables into the CFD simulation model, perform parameterized modeling on the structural parameters, generate multiple CFD simulation models of different working conditions, expand the CFD simulation model according to the analysis requirements of the irreversible loss type, build a multi-physics field simulation framework based on the CFD simulation model, and define the calculation method of each irreversible loss in the multi-physics field simulation framework; Step 2.3: Based on the M structural parameters and their levels of each component of the air compressor that affect the irreversible loss, select the corresponding orthogonal table to generate a parameter combination table, automatically import the parameter combination into the CFD simulation model constructed in step 2.2, and perform simulation calculations on all parameter combinations in turn. For each set of simulation results, extract the velocity field, temperature field and other related data, and apply wavelet denoising processing to the data.

3. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 2, characterized in that: In step 2.1, the structural parameters that affect the irreversible loss include but are not limited to: blade inlet installation angle, blade outlet installation angle, outlet blade thickness, volute cross-section ellipticity, volute outlet diameter, volute tongue angle, diffuser outlet radius, diffuser inlet diameter and diffuser outlet width.

4. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 2, characterized in that: In step 2.3, the flow loss in the multi-physics simulation framework is expressed by the entropy increase rate caused by viscous dissipation and turbulent dissipation. The entropy increase rate caused by viscous dissipation is determined by the following formula: Where: s v represents the entropy increase rate caused by viscous dissipation; μ represents the dynamic viscosity; T represents the thermodynamic temperature of the system; τ ij represents the viscous stress tensor; u i represents the velocity component in the i-th direction; x j represents the spatial coordinates of the jth direction; represents the velocity gradient; The rate of entropy increase due to turbulent dissipation is determined by: Where: s v’ represents the entropy increase rate caused by turbulent dissipation; β represents the empirical coefficient; ρ m represents fluid density, reflecting the mass of the fluid per unit volume; k represents turbulent kinetic energy; w represents turbulent frequency; T represents temperature; Thermodynamic losses are expressed by the rate of entropy increase due to the temperature gradient, which is determined by the following formula: Where: s t represents the entropy increase rate caused by temperature gradient; T represents temperature; k e represents the thermal conductivity; represents the temperature gradient; represents the square of the temperature gradient; Mechanical losses are expressed by the entropy increase rate due to wall friction, which is determined by the following formula: Where: s w represents the entropy increase rate caused by wall friction; τ w represents the wall shear stress; v represents the first layer grid velocity near the wall; T represents the temperature; The shock wave loss is expressed by the entropy increase rate caused by temperature fluctuations, which is determined by the following formula: Where: s t‘ represents the entropy increase rate caused by temperature pulsation; λ represents the thermal diffusivity; λ t represents the reference thermal diffusivity; s t It represents the rate of entropy increase caused by temperature gradient.

5. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 1, characterized in that: Step 3 includes: Step 3.1: Select multiple types of base models, build a base model library, divide the irreversible loss data into training subsets and test subsets, conduct independent training on each base model on its corresponding training subset, evaluate the performance of each base model on the test subset, calculate the corresponding mean square error, and assign initial weights through the reinforcement learning mechanism based on the evaluation results to complete the initialization of the base model library; Step 3.2: Initialize the reinforcement learning controller, set the controller parameters including state information, action set and reward function, receive the state information of the current base model, and the controller generates actions based on the state information. The actions include adjusting the weights of the base model or changing the model combination strategy; calculate the reward signal based on the overall model prediction performance, and optimize the controller strategy through the reinforcement learning algorithm; Step 3.3: Monitor the performance of the base models in real time, record the mean square error, computational complexity, and generalization ability, adjust the weights of the base models based on the reward mechanism, optimize the overall model performance by increasing the weights of the base models with good performance or reducing the weights of the base models with poor performance, dynamically select the model combination method based on the real-time data characteristics, and the model combination method includes linear weighted average and nonlinear weighted combination. Apply the updated weight distribution and combination strategy to the hybrid integration model to complete the dynamic adjustment; Step 3.4: Set the trade-off strategy between exploration and utilization behavior to determine whether the current state is to perform exploration behavior or utilization behavior. In the exploration phase, expand the search space by randomly perturbing the base model weights or introducing new model combination strategies. In the utilization phase, optimize the overall prediction performance by selecting the current best performing model combination strategy. Dynamically adjust the ratio of exploration and utilization based on historical reward feedback to achieve continuous optimization of the base model configuration and performance improvement.

6. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 5, characterized in that: In step 3.1, the base model includes but is not limited to deep neural network, support vector machine, classification regression decision tree, and long short-term memory network.

7. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 5, characterized in that: In step 3.2, the input controller state information includes the predicted mean square error, weight distribution and historical performance of the base model.

8. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 5, characterized in that: In step 3.2, the actions generated by the controller include adjusting the weights of the base model and changing the combination strategy of the base model. The combination strategy is to switch between linear weighted or nonlinear weighted combination methods.

9. The method for predicting irreversible loss of a fuel cell centrifugal air compressor according to claim 1, characterized in that: Step 1 includes: Step 1.1: Build a comprehensive performance test platform for fuel cell centrifugal air compressors, test the performance parameters, operating parameters and control parameters of centrifugal air compressors under the full range of working conditions, and obtain test data of the air compressors under different working conditions; Step 1.2: Use 3D modeling software to construct a 3D geometric model of the centrifugal air compressor; Step 1.3: Based on the test data measured in step 1.1 and the three-dimensional geometric model constructed in step 1.2, a multi-physics field coupling calculation CFD simulation model for the fuel cell centrifugal air compressor is established. The key performance parameters are calculated multiple times through the CFD simulation model to complete the convergence verification of the simulation results. The simulation calculation results are compared and analyzed with the test data obtained in step 1.1 to verify the convergence and accuracy of the CFD simulation model.

10. A fuel cell centrifugal air compressor irreversible loss prediction system, characterized in that: include: The data acquisition and model building module is used to collect the performance data of the air compressor under different boundary parameters based on the comprehensive performance test platform of the fuel cell centrifugal air compressor, and to establish a multi-physics field coupling calculation CFD simulation model of the fuel cell centrifugal air compressor in combination with the three-dimensional geometric model of the centrifugal air compressor, and to verify the convergence and accuracy of the CFD simulation model; The parameter optimization and key data extraction module is used to define N types of irreversible loss for different parts of the air compressor, and determine M structural parameters related to the irreversible loss based on the structural characteristics of each part. Based on the CFD simulation model of the fuel cell air compressor, an integrated CFD simulation framework is constructed, and the number of levels and parameter combinations of the M structural parameters are determined by designing orthogonal experiments, and a parameter combination table is generated. The parameter combination table is imported into the CFD simulation framework, and the CFD simulation framework is used to perform simulation calculations on all parameter combinations in the parameter combination table in turn, and key data corresponding to each type of irreversible loss is extracted from each group of simulation results; The prediction model construction module is used to propose the RL-GHEM method, build multiple base models to form a model library, independently train and evaluate the performance of each base model, introduce a reinforcement learning controller, generate actions to adjust the base model weights or change the model combination strategy, optimize the weights of the base models through the reward and penalty mechanism, dynamically switch between linear weighted combination and nonlinear combination methods according to real-time data characteristics, and dynamically optimize the base model weights and combination strategies using the exploration and utilization balance strategy to construct an irreversible loss prediction model for air compressors under different working conditions.

Images