Hydraulic and thermal fluid dynamic lubrication calculation model and optimization method

Abstract

The invention relates to the technical field of hydraulic systems, in particular to a hydraulic and thermal fluid dynamic lubrication calculation model and an optimization method, comprising the following steps: S1, modeling a multi-scale heterogeneous system; s2, carrying out heat-friction-viscosity synergistic effect modeling; and S3, dynamic boundary lubrication and lubricant behavior prediction. According to the method, by integrating nanoscale, mesoscale and macroscopic level lubrication system modeling, physical phenomena on different scales and interaction of the physical phenomena are comprehensively captured, and the step covers multiple aspects of multi-scale heterogeneous system modeling, nanoscale lubrication behavior modeling, macroscopic fluid field and structure field coupling and the like; high-precision predictive capacity and systematic thermal management are achieved by combining multiple physical fields such as heat, friction, viscosity and fluid dynamics, through collaborative modeling of multiple scales and multiple physical fields, the accuracy and stability of a lubricating system are improved, a solid theoretical basis is provided for optimization design, and the method is suitable for popularization and application. And stable operation in high-load and high-temperature environments is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic systems, and in particular to a hydraulic and thermal fluid dynamic lubrication calculation model and an optimization method. Background Art

[0002] Hydraulic systems and thermofluid dynamic lubrication technologies are widely used in mechanical equipment, automobiles, aerospace, industrial manufacturing and other fields. Especially in high-load, high-temperature, and high-speed operating environments, the role of the lubrication system is crucial. Traditional lubrication models mostly focus on macroscopic fluid dynamics analysis, fail to fully consider the lubrication behavior at the nanoscale and mesoscale, and fail to effectively couple multiple physical phenomena such as heat, friction, and fluid dynamics. This results in the inability of existing lubrication systems to accurately predict lubrication performance when facing complex working conditions, which in turn affects the efficiency and reliability of mechanical systems. Especially under extreme working conditions, the lubrication effect is often unstable, causing excessive wear, energy loss, and failure of equipment.

[0003] In the existing technology, most of the traditional hydraulic and thermal fluid dynamic lubrication models have the following defects: many existing models only consider fluid dynamics and thermal management at the macro level, ignoring the nano-level lubrication behavior and its impact on the performance of the entire system, resulting in insufficient accuracy in the prediction of lubrication effects; most traditional models are based on the analysis method of a single physical field, and fail to effectively couple multiple physical fields (such as friction, fluid dynamics, heat conduction, etc.), lacking systematic overall optimization; most traditional optimization methods rely on static mathematical models and empirical data, which are difficult to cope with dynamic changes under actual working conditions, and cannot achieve intelligent and automated real-time adjustment and feedback. Therefore, we provide a hydraulic and thermal fluid dynamic lubrication calculation model and optimization method. Summary of the invention

[0004] In view of the above shortcomings of the prior art, the first purpose of the present invention is to provide a hydraulic and thermal fluid dynamic lubrication calculation model and optimization method to solve the problems in the above background technology.

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

[0006] A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method, comprising the following steps:

[0007] S1. Multiscale heterogeneous system modeling;

[0008] S2, modeling of thermal-friction-viscosity synergy effects;

[0009] S3, Dynamic boundary lubrication and prediction of lubricant behavior;

[0010] S4, reversible thermofluidic analysis;

[0011] S5, highly coupled multi-domain collaborative optimization;

[0012] S6, topological dynamics optimization;

[0013] S7. Dynamic prediction and control based on machine learning;

[0014] S8. Generative experimental verification and model improvement.

[0015] The present invention is further configured as follows: in the step S1, multi-scale heterogeneous system modeling:

[0016] S1.1. Using LAMMPS molecular dynamics simulation software, we selected typical poly-α-olefin lubricant molecules and specific atomic structure models of metal steel surface materials, applied shear stress at the atomic scale, observed the arrangement, slip and fracture behavior of lubricant molecules, accurately captured the changes in microscopic forces, van der Waals forces and hydrogen bonds, and simulated temperature control under actual working conditions (300K to 500K);

[0017] S1.2. Use the lattice Boltzmann method to simulate the dynamic changes of the lubricating film at the micrometer scale, construct a two-dimensional or three-dimensional lattice model with actual geometric dimensions (100μm × 100μm × 10μm), set boundary conditions to simulate the pressure and velocity distribution under real working conditions, and study the evolution of the lubricating film thickness over time by introducing a multiphase fluid model, and analyze the film stability of the lubricant at different shear rates and temperatures;

[0018] S1.3, combining computational fluid dynamics and ANSYS finite element analysis tools, constructing a joint model of macro fluid field and solid structure field, setting the fluid inlet velocity, pressure boundary conditions, and elastic modulus and yield strength of solid materials, simulating the response of the lubrication system under actual working loads, and seamlessly coupling the two simulation methods;

[0019] S1.4. Select lubricating materials containing micropores (pore size of 10-100 nanometers) and particle reinforcement structures (carbon nanotubes), use the finite element method to analyze their stress distribution and deformation characteristics under dynamic lubrication conditions, determine the mechanical properties of the materials (such as Young's modulus, Poisson's ratio and fracture toughness) through experiments, and apply these data in simulations to evaluate the stability and durability of the materials under high stress and high temperature environments.

[0020] The present invention is further configured as follows: in the step S2, heat-friction-viscosity synergistic effect modeling:

[0021] S2.1. Establish a friction heat accumulation model based on finite element analysis, select appropriate heat conduction equations and parameters for converting friction work into thermal energy, simulate the temperature rise of the local area (contact surface), and calibrate the model parameters by experimentally measuring the friction coefficient under different pressure and speed conditions;

[0022] S2.2. Carreau non-Newtonian fluid model is used to describe the viscosity change of lubricants at high shear rates. Combined with fluid dynamics simulation, the effects of different shear rates on lubricating film thickness and stability are studied. The viscosity data of lubricants at different shear rates are obtained through rheological experiments (rotational viscometer) and applied to the numerical model.

[0023] S2.3. Construct a chemical degradation model of lubricants under high temperature conditions, taking into account oxidation, polymerization and cracking reactions, and using experimental techniques such as thermogravimetric analysis and Fourier transform infrared spectroscopy to obtain data on the chemical changes of lubricants at different temperatures, input the data into the model for simulation, and predict the performance degradation of lubricants in long-term operation;

[0024] S2.4. By optimizing the cooling path design, using CFD to simulate the temperature distribution of key parts (bearings and gears), setting the flow and temperature of the water-cooled cooling medium, adjusting the cooling path geometry, minimizing the temperature rise of key parts, and combining thermocouple monitoring experimental measurements to verify the effectiveness of the optimized design.

[0025] The present invention is further configured as follows: in the step S3, dynamic boundary lubrication and lubricant behavior prediction:

[0026] S3.1. Simulate the changes in viscosity and surface adhesion performance of responsive lubricants under different pressure and temperature conditions, select thermosensitive polymer lubricant materials with intelligent response characteristics, analyze the behavior changes of their molecular structures under different stimuli through molecular dynamics simulation, and predict the dynamic response of lubrication performance;

[0027] S3.2, using deformation boundary theory to simulate the flow and film thickness change of lubricant under high dynamic impact conditions, constructing dynamic boundary conditions impact load and instantaneous velocity change, and using CFD and FEM to jointly simulate the response of lubricating film under extreme conditions to evaluate its stability and impact resistance;

[0028] S3.3. Apply density functional theory to calculate the interaction energy and binding mode between lubricant molecules and metal surfaces. Select copper metal materials and lubricant molecules, and simulate different surface modifications and lubricant molecule arrangements through DFT to reveal the lubrication mechanism at the molecular level.

[0029] S3.4. Simulate the uniform distribution of silica nanoparticles in the lubricant and evaluate its effect on improving the lubrication performance. Through the multiphase fluid model, study the dispersion stability of nanoadditives under different shear conditions and optimize the particle size and concentration of the additives to achieve the best lubrication effect.

[0030] The present invention is further configured as follows: in the step S4, reversible thermofluidic analysis:

[0031] S4.1. Establish a secondary utilization model of friction heat, select a heat exchanger recovery device to simulate the heat energy transfer and reuse process of the local heat source (bearing area), use thermal fluid dynamics simulation to evaluate the recovery efficiency, and optimize the heat recovery path and equipment parameters;

[0032] S4.2. Study the design of low temperature difference heat transfer, optimize the flow path of heat transfer medium and the structure of heat exchanger to achieve quasi-reversible heat conduction, and use genetic algorithm to adjust the design parameters to minimize heat loss;

[0033] S4.3. Apply dissipative structure theory to analyze unnecessary energy dissipation processes in lubrication systems, and minimize energy dissipation by identifying and quantifying the sources of energy loss in the system (fluid viscosity dissipation and heat conduction loss), improving fluid flow paths, and enhancing thermal insulation;

[0034] S4.4. Design a self-circulating fluid cooling path, utilize the fluid's own circulation kinetic energy and heat conduction characteristics to optimize the dissipation of friction heat, and optimize the geometry of the cooling path and fluid flow rate through CFD simulation to ensure that the temperature of key parts is controlled within a safe range.

[0035] The present invention is further configured as follows: in the step S5, highly coupled multi-domain collaborative optimization:

[0036] S5.1. Construct a composite objective function covering lubrication performance, thermal stability and pressure balance, combine the multi-objective optimization method (weighted sum method), set the weight coefficient of each objective, and ensure the balance and coordination of various performance indicators during the optimization process through parameter scanning and sensitivity analysis;

[0037] S5.2. Use MPI distributed computing technology to accelerate the multi-objective optimization process of complex models, distribute different sub-models of the lubrication system (fluid dynamics, heat conduction and structural response) to multiple computing nodes for parallel processing, improve optimization efficiency and calculation accuracy, and shorten the optimization cycle;

[0038] S5.3. Establish a real-time feedback mechanism based on a sensor network to collect the operating data of the lubrication system (temperature, pressure and flow rate), and adjust the optimization parameters (lubricant flow and cooling medium temperature) in real time through the PID control algorithm to achieve dynamic control and adaptive optimization of the system;

[0039] S5.4. Analyze the robustness of the optimization model under parameter uncertainty through Monte Carlo simulation, set the probability distribution of each optimization parameter, perform a large number of random sampling and simulations, and evaluate the changing trend of system performance under different uncertainty conditions.

[0040] The present invention is further configured as follows: in the step S6, topology dynamics optimization:

[0041] S6.1. Study the topological change law of lubricating film under dynamic load. Select different load conditions (cyclic loading and impact loading), simulate the morphological evolution of lubricating film through finite element analysis and SIMP topological optimization algorithm, and identify the structural changes and stress concentration points in key areas.

[0042] S6.2. Optimize the thickness distribution and geometry of the lubricating film, and use the topology optimization tool (ANSYS TopologyOptimization) to design a lubricating film structure that can effectively disperse and relieve local stress concentration. Combined with digital image correlation technology experimental stress testing, verify the stress relief effect of the design and ensure the stability of the lubricating film under high stress environment;

[0043] S6.3. Design a lubrication path topology model that automatically adjusts based on dynamic pressure changes. Use fluid mechanics simulation and intelligent control algorithms to ensure that lubricants can be intelligently diverted to required areas under different pressure conditions. Verify the response speed and diversion efficiency of the intelligent diversion system through experimental fluid testing (fluid path visualization and particle image velocimetry).

[0044] S6.4. Use graph theory methods to optimize the distribution efficiency of the lubrication path, construct a network model of the lubrication system, and use the shortest path algorithm or maximum flow minimum cut theory to optimize the lubricant distribution path. Through simulation and experimental testing, verify the performance improvement of the optimized path network in actual operation.

[0045] The present invention is further configured as follows: in the step S7, dynamic prediction and regulation based on machine learning:

[0046] S7.1. Use convolutional deep neural networks to replace complex numerical calculation processes and build a model that can quickly predict the behavior of the lubrication system. Train the network with large-scale simulation data or experimental data to significantly accelerate the model simulation speed while maintaining high prediction accuracy, which is suitable for real-time application scenarios.

[0047] S7.2. Collect historical operating data of the lubrication system, such as temperature, pressure, flow rate, and wear rate. Use multivariate regression analysis or support vector machine machine learning methods to establish a prediction model for lubrication performance changes with operating conditions. Through cross-validation and performance evaluation, ensure the prediction ability and generalization performance of the model, and provide data support for system maintenance and optimization.

[0048] S7.3. Apply the Q-learning reinforcement learning algorithm to optimize lubrication parameters (lubricant flow and temperature) in real time under dynamic conditions, build an environmental model of the lubrication system, define the reward function (lubrication efficiency and energy consumption), and achieve adaptive optimization of lubrication parameters through continuous learning and exploration of the intelligent agent;

[0049] S7.4. Design an adaptive control algorithm based on machine learning to dynamically adjust the operating parameters of the lubrication system using real-time data (temperature and pressure monitored by sensors). Use online learning and model updating techniques to enable the control strategy to self-adjust as the system state changes, ensuring stable operation and efficient lubrication under different operating conditions.

[0050] The present invention is further configured as follows: in the step S8, generative experimental verification and model improvement:

[0051] S8.1. Use digital twin technology to establish a virtual experimental environment for the lubrication system. By integrating the geometry, materials, and operating parameters of the actual system, a high-precision digital model is created to support real-time data synchronization and dynamic simulation. The virtual platform is used to conduct simulation tests under various working conditions, predict system behavior and performance, and provide guidance for experimental design.

[0052] S8.2. Use the inversion method to infer the key parameters (friction coefficient and thermal conductivity coefficient) in the optimization model through experimental data, design the experimental plan (tests under different load and speed conditions), collect actual operation data, compare them with the model prediction results, adjust and calibrate the optimization parameters, and ensure the accuracy and reliability of the model;

[0053] S8.3. Realize two-way iterative improvement of experiments and simulations, verify the prediction results of the simulation model through experiments, adjust the simulation model parameters according to the experimental feedback, design a series of gradually complex experiments (different temperature, pressure and load conditions), and continuously optimize the model structure and parameter settings;

[0054] S8.4. Simulate the operation of the lubrication system under extreme conditions (high temperature, high pressure, and high-speed impact) in virtual and real environments, conduct preliminary tests on the virtual experimental platform to screen out potential design problems and performance bottlenecks, and then verify them in actual experiments to ensure the robustness and reliability of the model under various extreme conditions.

[0055] Beneficial Effects

[0056] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0057] 1. The present invention comprehensively captures physical phenomena at different scales and their interactions by integrating lubrication system modeling at the nanoscale, mesoscale and macroscale levels. This step covers multiple aspects such as multi-scale inhomogeneous system modeling, nanoscale lubrication behavior modeling, coupling of macroscopic fluid field and structural field, etc., and combines multiple physical fields such as heat, friction, viscosity and fluid dynamics to achieve high-precision prediction capabilities and systematic thermal management. Through this multi-scale, multi-physical field collaborative modeling, not only the accuracy and stability of the lubrication system are improved, but also a solid theoretical basis is provided for optimized design, ensuring stable operation under high load and high temperature environments.

[0058] 2. The present invention realizes intelligent control and adaptive adjustment of the lubrication system by utilizing a highly coupled multi-domain collaborative optimization method combined with machine learning and reinforcement learning algorithms. This step includes coupled optimization objective function design, real-time regulation feedback mechanism modeling, model simplification based on deep learning, etc. At the same time, the accuracy and robustness of the model are ensured through joint verification of the virtual experimental platform and actual experiments. This process not only improves the optimization efficiency and reliability of the system in multiple performance indicators, but also enhances the adaptability and stability of the system under complex working conditions. Through continuous model calibration and optimization, the reliability and practicability of engineering applications are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a hydraulic and thermal fluid dynamic lubrication calculation model and optimization method of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] The present invention will be further described below in conjunction with the embodiments.

[0062] Example 1

[0063] like Figure 1 As shown, the present invention provides a technical solution: a hydraulic and thermal fluid dynamic lubrication calculation model and optimization method, in the step S1, multi-scale heterogeneous system modeling:

[0064] S1.1. Using LAMMPS molecular dynamics simulation software, we selected typical poly-α-olefin lubricant molecules and specific atomic structure models of metal steel surface materials, applied shear stress at the atomic scale, observed the arrangement, slip and fracture behavior of lubricant molecules, accurately captured the changes in microscopic forces, van der Waals forces and hydrogen bonds, and simulated temperature control under actual working conditions (300K to 500K);

[0065] S1.2. Use the lattice Boltzmann method to simulate the dynamic changes of the lubricating film at the micrometer scale, construct a two-dimensional or three-dimensional lattice model with actual geometric dimensions (100μm × 100μm × 10μm), set boundary conditions to simulate the pressure and velocity distribution under real working conditions, and study the evolution of the lubricating film thickness over time by introducing a multiphase fluid model, and analyze the film stability of the lubricant at different shear rates and temperatures;

[0066] S1.3, combining computational fluid dynamics and ANSYS finite element analysis tools, constructing a joint model of macro fluid field and solid structure field, setting the fluid inlet velocity, pressure boundary conditions, and elastic modulus and yield strength of solid materials, simulating the response of the lubrication system under actual working loads, and seamlessly coupling the two simulation methods;

[0067] S1.4. Select lubricating materials with micropores (pore size of 10-100 nm) and particle reinforcement structures (carbon nanotubes), use the finite element method to analyze their stress distribution and deformation characteristics under dynamic lubrication conditions, experimentally determine the mechanical properties of the materials (such as Young's modulus, Poisson's ratio and fracture toughness), and apply these data in simulations to evaluate the stability and durability of the materials under high stress and high temperature environments;

[0068] In the step S2, heat-friction-viscosity synergistic effect modeling:

[0069] S2.1. Establish a friction heat accumulation model based on finite element analysis, select appropriate heat conduction equations and parameters for converting friction work into thermal energy, simulate the temperature rise of the local area (contact surface), and calibrate the model parameters by experimentally measuring the friction coefficient under different pressure and speed conditions;

[0070] S2.2. Carreau non-Newtonian fluid model is used to describe the viscosity change of lubricants at high shear rates. Combined with fluid dynamics simulation, the effects of different shear rates on lubricating film thickness and stability are studied. The viscosity data of lubricants at different shear rates are obtained through rheological experiments (rotational viscometer) and applied to the numerical model.

[0071] S2.3. Construct a chemical degradation model of lubricants under high temperature conditions, taking into account oxidation, polymerization and cracking reactions, and using experimental techniques such as thermogravimetric analysis and Fourier transform infrared spectroscopy to obtain data on the chemical changes of lubricants at different temperatures, input the data into the model for simulation, and predict the performance degradation of lubricants in long-term operation;

[0072] S2.4. By optimizing the cooling path design, using CFD to simulate the temperature distribution of key parts (bearings and gears), setting the flow rate and temperature of the water-cooled cooling medium, adjusting the cooling path geometry, minimizing the temperature rise of key parts, and combining thermocouple monitoring experimental measurements to verify the effectiveness of the optimized design;

[0073] In the step S3, dynamic boundary lubrication and lubricant behavior prediction:

[0074] S3.1. Simulate the changes in viscosity and surface adhesion performance of responsive lubricants under different pressure and temperature conditions, select thermosensitive polymer lubricant materials with intelligent response characteristics, analyze the behavior changes of their molecular structures under different stimuli through molecular dynamics simulation, and predict the dynamic response of lubrication performance;

[0075] S3.2, using deformation boundary theory to simulate the flow and film thickness change of lubricant under high dynamic impact conditions, constructing dynamic boundary conditions impact load and instantaneous velocity change, and using CFD and FEM to jointly simulate the response of lubricating film under extreme conditions to evaluate its stability and impact resistance;

[0076] S3.3. Apply density functional theory to calculate the interaction energy and binding mode between lubricant molecules and metal surfaces. Select copper metal materials and lubricant molecules, and simulate different surface modifications and lubricant molecule arrangements through DFT to reveal the lubrication mechanism at the molecular level.

[0077] S3.4. Simulate the uniform distribution of silica nanoparticles in lubricants to evaluate their effect on improving lubrication performance. Use a multiphase fluid model to study the dispersion stability of nanoadditives under different shear conditions and optimize the particle size and concentration of additives to achieve the best lubrication effect.

[0078] In the step S4, reversible thermofluidic analysis:

[0079] S4.1. Establish a secondary utilization model of friction heat, select a heat exchanger recovery device to simulate the heat energy transfer and reuse process of the local heat source (bearing area), use thermal fluid dynamics simulation to evaluate the recovery efficiency, and optimize the heat recovery path and equipment parameters;

[0080] S4.2. Study the design of low temperature difference heat transfer, optimize the flow path of heat transfer medium and the structure of heat exchanger to achieve quasi-reversible heat conduction, and use genetic algorithm to adjust the design parameters to minimize heat loss;

[0081] S4.3. Apply dissipative structure theory to analyze unnecessary energy dissipation processes in lubrication systems, and minimize energy dissipation by identifying and quantifying the sources of energy loss in the system (fluid viscosity dissipation and heat conduction loss), improving fluid flow paths, and enhancing thermal insulation;

[0082] S4.4. Design a self-circulating fluid cooling path, utilize the fluid's own circulation kinetic energy and heat conduction characteristics to optimize the dissipation of friction heat, and optimize the geometry of the cooling path and fluid flow rate through CFD simulation to ensure that the temperature of key parts is controlled within a safe range.

[0083] In this embodiment, by integrating the lubrication system modeling at the nanoscale, mesoscale and macroscale levels, the physical phenomena at different scales and their interactions are fully captured. This step covers multiple aspects such as multi-scale inhomogeneous system modeling, nanoscale lubrication behavior modeling, and coupling of macroscopic fluid fields and structural fields. It combines multiple physical fields such as heat, friction, viscosity and fluid dynamics to achieve high-precision prediction capabilities and systematic thermal management. Through this multi-scale, multi-physical field collaborative modeling, not only the accuracy and stability of the lubrication system are improved, but also a solid theoretical basis is provided for optimized design, ensuring stable operation under high load and high temperature environments.

[0084] Example 2

[0085] like Figure 1 As shown, the present invention provides a technical solution: a hydraulic and thermal fluid dynamic lubrication calculation model and optimization method, in the step S5, highly coupled multi-domain collaborative optimization:

[0086] S5.1. Construct a composite objective function covering lubrication performance, thermal stability and pressure balance, combine the multi-objective optimization method (weighted sum method), set the weight coefficient of each objective, and ensure the balance and coordination of various performance indicators during the optimization process through parameter scanning and sensitivity analysis;

[0087] S5.2. Use MPI distributed computing technology to accelerate the multi-objective optimization process of complex models, distribute different sub-models of the lubrication system (fluid dynamics, heat conduction and structural response) to multiple computing nodes for parallel processing, improve optimization efficiency and calculation accuracy, and shorten the optimization cycle;

[0088] S5.3. Establish a real-time feedback mechanism based on a sensor network to collect the operating data of the lubrication system (temperature, pressure and flow rate), and adjust the optimization parameters (lubricant flow and cooling medium temperature) in real time through the PID control algorithm to achieve dynamic control and adaptive optimization of the system;

[0089] S5.4. Analyze the robustness of the optimization model under parameter uncertainty through Monte Carlo simulation, set the probability distribution of each optimization parameter, perform a large number of random sampling and simulations, and evaluate the changing trend of system performance under different uncertainty conditions;

[0090] In the step S6, topology dynamics optimization:

[0091] S6.1. Study the topological change law of lubricating film under dynamic load. Select different load conditions (cyclic loading and impact loading), simulate the morphological evolution of lubricating film through finite element analysis and SIMP topological optimization algorithm, and identify the structural changes and stress concentration points in key areas.

[0092] S6.2. Optimize the thickness distribution and geometry of the lubricating film, and use the topology optimization tool (ANSYS TopologyOptimization) to design a lubricating film structure that can effectively disperse and relieve local stress concentration. Combined with digital image correlation technology experimental stress testing, verify the stress relief effect of the design and ensure the stability of the lubricating film under high stress environment;

[0093] S6.3. Design a lubrication path topology model that automatically adjusts based on dynamic pressure changes. Use fluid mechanics simulation and intelligent control algorithms to ensure that lubricants can be intelligently diverted to required areas under different pressure conditions. Verify the response speed and diversion efficiency of the intelligent diversion system through experimental fluid testing (fluid path visualization and particle image velocimetry).

[0094] S6.4. Use graph theory to optimize the distribution efficiency of lubrication paths, construct a network model of the lubrication system, and use the shortest path algorithm or maximum flow minimum cut theory to optimize the distribution path of the lubricant. Through simulation and experimental testing, verify the performance improvement of the optimized path network in actual operation;

[0095] In the step S7, dynamic prediction and regulation based on machine learning:

[0096] S7.1. Use convolutional deep neural networks to replace complex numerical calculation processes and build a model that can quickly predict the behavior of the lubrication system. Train the network with large-scale simulation data or experimental data to significantly accelerate the model simulation speed while maintaining high prediction accuracy, which is suitable for real-time application scenarios.

[0097] S7.2. Collect historical operating data of the lubrication system, such as temperature, pressure, flow rate, and wear rate. Use multivariate regression analysis or support vector machine machine learning methods to establish a prediction model for lubrication performance changes with operating conditions. Through cross-validation and performance evaluation, ensure the prediction ability and generalization performance of the model, and provide data support for system maintenance and optimization.

[0098] S7.3. Apply the Q-learning reinforcement learning algorithm to optimize lubrication parameters (lubricant flow and temperature) in real time under dynamic conditions, build an environmental model of the lubrication system, define the reward function (lubrication efficiency and energy consumption), and achieve adaptive optimization of lubrication parameters through continuous learning and exploration of the intelligent agent;

[0099] S7.4. Design an adaptive control algorithm based on machine learning to dynamically adjust the operating parameters of the lubrication system using real-time data (temperature and pressure monitored by sensors). Use online learning and model updating techniques to enable the control strategy to self-adjust as the system state changes, ensuring stable operation and efficient lubrication under different operating conditions.

[0100] In the step S8, generative experimental verification and model improvement:

[0101] S8.1. Use digital twin technology to establish a virtual experimental environment for the lubrication system. By integrating the geometry, materials, and operating parameters of the actual system, a high-precision digital model is created to support real-time data synchronization and dynamic simulation. The virtual platform is used to conduct simulation tests under various working conditions, predict system behavior and performance, and provide guidance for experimental design.

[0102] S8.2. Use the inversion method to infer the key parameters (friction coefficient and thermal conductivity coefficient) in the optimization model through experimental data, design the experimental plan (tests under different load and speed conditions), collect actual operation data, compare them with the model prediction results, adjust and calibrate the optimization parameters, and ensure the accuracy and reliability of the model;

[0103] S8.3. Realize two-way iterative improvement of experiments and simulations, verify the prediction results of the simulation model through experiments, adjust the simulation model parameters according to the experimental feedback, design a series of gradually complex experiments (different temperature, pressure and load conditions), and continuously optimize the model structure and parameter settings;

[0104] S8.4. Simulate the operation of the lubrication system under extreme conditions (high temperature, high pressure, and high-speed impact) in virtual and real environments, conduct preliminary tests on the virtual experimental platform to screen out potential design problems and performance bottlenecks, and then verify them in actual experiments to ensure the robustness and reliability of the model under various extreme conditions.

[0105] In this embodiment, by utilizing a highly coupled multi-domain collaborative optimization method combined with machine learning and reinforcement learning algorithms, intelligent control and adaptive adjustment of the lubrication system are achieved. This step includes coupled optimization objective function design, real-time control feedback mechanism modeling, and model simplification based on deep learning. At the same time, the accuracy and robustness of the model are ensured through joint verification of the virtual experimental platform and actual experiments. This process not only improves the optimization efficiency and reliability of the system in multiple performance indicators, but also enhances the adaptability and stability of the system under complex working conditions. Through continuous model calibration and optimization, the reliability and practicability of engineering applications are significantly improved.

[0106] In the actual use process, the present invention accurately simulates the interaction between lubricants and metal surfaces at different scales through multi-scale heterogeneous system modeling. The molecular dynamics simulation software LAMMPS is used to analyze the arrangement, slip and fracture behavior of lubricant molecules, and the lattice Boltzmann method is used to study the dynamic changes of lubricating films at the micrometer scale. At the same time, combined with computational fluid dynamics and finite element analysis tools, a joint model of macroscopic fluid field and solid structure field is constructed to comprehensively capture physical phenomena and their interactions from the atomic level to the macroscopic level, ensuring the stability and durability of the lubrication system under high stress and high temperature environments.

[0107] The model comprehensively simulates the heat accumulation, lubricating film thickness change and lubricant performance degradation of the lubrication system in actual operation by establishing the heat-friction-viscosity synergy effect and dynamic boundary lubrication prediction mechanism. The friction heat accumulation model is established by finite element analysis, the Carreau non-Newtonian fluid model is used to describe the viscosity change of the lubricant under high shear rate, and the chemical degradation model of the lubricant under high temperature conditions is constructed. At the same time, by optimizing the cooling path design and dynamic boundary condition simulation, the temperature of key parts is ensured to be controlled within a safe range, and the stability and impact resistance of the lubricating film are improved.

[0108] It integrates highly coupled multi-domain collaborative optimization methods and machine learning algorithms to achieve intelligent control and adaptive adjustment of the lubrication system. Through multi-objective optimization, distributed computing and real-time feedback mechanisms, it optimizes lubrication performance, thermal stability and pressure balance, and uses convolutional deep neural networks and reinforcement learning algorithms for dynamic prediction and parameter optimization. At the same time, digital twin technology and experimental verification methods are used to continuously calibrate and improve the model to ensure its accuracy and robustness under various complex working conditions. Through this multi-scale, multi-physics field collaborative modeling and optimization, the operating efficiency and reliability of the lubrication system under high load and high temperature environments have been significantly improved.

[0109] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method, characterized in that: The following steps are involved: S1. Multiscale heterogeneous system modeling; S2, modeling of thermal-friction-viscosity synergy effects; S3, Dynamic boundary lubrication and prediction of lubricant behavior; S4, reversible thermofluidic analysis; S5, highly coupled multi-domain collaborative optimization; S6, topological dynamics optimization; S7. Dynamic prediction and control based on machine learning; S8. Generative experimental verification and model improvement.

2. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S1, multi-scale heterogeneous system modeling: S1.

1. Study the microscopic behavior of lubricant molecules through molecular dynamics simulation and capture the microscopic forces; S1.

2. Apply the lattice Boltzmann method to study the dynamic changes of lubricant film thickness at the mesoscopic scale; S1.3, use CFD and FEM joint modeling to seamlessly couple the macro fluid field with the solid stress state; S1.

4. Analyze the properties of materials containing micropores and particle reinforcement structures under dynamic lubrication conditions.

3. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S2, heat-friction-viscosity synergistic effect modeling: S2.

1. Construct a friction heat accumulation model to analyze the dynamic effect of local temperature rise on viscosity; S2.

2. Study the viscosity change of lubricants at high shear rates and its effect on lubrication performance; S2.

3. Establish a lubricant degradation model to simulate the process of lubricant chemical property degradation under high temperature conditions; S2.

4. Reduce the temperature rise of key parts by optimizing the cooling path design.

4. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S3, dynamic boundary lubrication and lubricant behavior prediction: S3.1, simulate the changes in viscosity and surface adhesion properties of responsive lubricants under pressure, temperature and other stimuli; S3.2, using deformation boundary theory to analyze lubricant flow and film thickness changes under high dynamic impact conditions; S3.

3. Apply density functional theory to calculate the interaction between lubricant molecules and metal surfaces; S3.

4. Simulate the uniform distribution of nanoparticles in the lubricant.

5. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S4, reversible thermofluidic analysis: S4.

1. Construct a thermal fluid energy recovery model to analyze the possibility of secondary utilization of local friction heat; S4.

2. Study the realization of quasi-reversible heat transfer through low temperature difference heat transfer design; S4.

3. Use dissipative structure theory to analyze the unnecessary dissipation of energy in lubrication systems; S4.

4. Introduce a self-circulating fluid cooling path to optimize frictional heat effects.

6. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S5, highly coupled multi-domain collaborative optimization: S5.

1. Construct a composite objective function that simultaneously optimizes lubrication performance, thermal stability, and pressure balance; S5.

2. Use distributed computing technology to accelerate multi-objective optimization of complex models; S5.

3. Establish a real-time feedback mechanism based on sensor networks to adjust optimization parameters; S5.

4. Analyze the robustness of the optimization model through Monte Carlo simulation.

7. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S6, topology dynamics optimization: S6.

1. Study the topological change of lubricating film under dynamic load; S6.

2. Optimize the lubricating film thickness distribution to alleviate local stress concentration; S6.

3. Design a topological model that can automatically adjust the lubrication path according to dynamic changes in pressure; S6.

4. Optimize the distribution efficiency of lubrication paths through graph theory.

8. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S7, dynamic prediction and regulation based on machine learning: S7.

1. Use deep neural networks to replace complex numerical calculation processes to accelerate model simulation; S7.

2. Use historical operating data and multivariate regression to predict performance changes in lubrication systems; S7.

3. Apply reinforcement learning to optimize lubrication parameters in real time under dynamic conditions; S7.

4. Design an adaptive control algorithm based on machine learning to achieve online regulation.

9. A hydraulic and thermal fluid dynamic lubrication calculation model and optimization method according to claim 1, characterized in that: In the step S8, generative experimental verification and model improvement: S8.

1. Use digital twin technology to establish a virtual experimental environment for the lubrication system; S8.

2. Verify the rationality of the optimization parameters through experimental inversion method; S8.3, realize the two-way iterative improvement model of experiment and simulation; S8.

4. Test the robustness of the model by simulating extreme working conditions in virtual and real environments.

Images