Space environment welding digital twinning method based on multi-scale dynamic coupling

Abstract

The invention discloses a space environment welding digital twinning method based on multi-scale dynamic coupling, which comprises the following steps: S1, collecting key data in a welding process, and establishing a basic numerical model of the welding process and tissue change in combination with experimental data; s2, on the basis of the basic numerical model, a numerical simulation method is adopted to construct a digital twinborn model of the welding process; s3, establishing a real-time data interaction mechanism between the digital model and actual welding equipment by utilizing a virtual-real synchronization model in the digital twin model; s4, on the basis of feedback data obtained by a real-time data interaction mechanism, welding process parameters are automatically adjusted through an intelligent optimization model in the digital twin model, so that the structure change in the welding process is matched with a target prediction result; and S5, establishing a welding process data management database, storing the key data and the adjusted process parameters, and continuously training and optimizing the prediction precision of the digital twin model based on historical data in the database.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aerospace manufacturing, and particularly relates to a space environment welding digital twinning method based on multi-scale dynamic coupling. BACKGROUND

[0002] With the rapid development of aerospace technology and the continuous expansion of deep space exploration missions, the welding quality requirements of spacecraft structural components are becoming increasingly stringent. Welding operations in space environments face extreme challenges that are not present in ground environments, including the coupling of multiple complex factors such as large amplitude temperature cycling, microgravity conditions, atomic oxygen corrosion, etc. These factors have a significant impact on the thermal cycle, molten pool behavior, microstructure evolution, and joint performance of the welding process.

[0003] Traditional welding process parameter design and quality control methods are mainly based on ground environmental conditions, and their theoretical models and experimental data are difficult to directly apply to space environments. Existing welding process modeling methods usually use single-scale analysis, which cannot effectively describe the multi-scale coupling mechanism between atomic-scale material phase transition and macro-scale structural deformation, resulting in insufficient prediction accuracy of the welding process in space environments.

[0004] Therefore, there is an urgent need for a space environment welding digital twinning method based on multi-scale dynamic coupling. SUMMARY

[0005] The present application provides a space environment welding digital twinning method based on multi-scale dynamic coupling to solve the above problems in the prior art.

[0006] In order to achieve the above purpose, the present application provides the following technical scheme:

[0007] A space environment welding digital twinning method based on multi-scale dynamic coupling, comprising:

[0008] S1: Collecting key data during the welding process, and establishing a basic numerical model of the welding process and microstructure evolution based on experimental data;

[0009] S2: Based on the basic numerical model, a digital twinning model of the welding process is constructed using numerical simulation methods, and the digital twinning model integrates a space environment dynamic model, a multi-scale coupling model, an intelligent optimization model, and a virtual-real synchronization model;

[0010] S3: Using the virtual-real synchronization model in the digital twinning model, a real-time data interaction mechanism between the digital model and the actual welding equipment is established;

[0011] S4: Based on the feedback data obtained through the real-time data interaction mechanism, the intelligent optimization model in the digital twinning model automatically adjusts the welding process parameters so that the microstructure evolution of the welding process matches the target prediction results.

[0012] S5: Establish a welding process data management database to store key data and adjusted process parameters, and continuously train the prediction accuracy of the optimized digital twin model based on historical data in the database.

[0013] The S1 step includes:

[0014] S11: Collect key data of temperature field, micro-gravity disturbance and material corrosion in space welding process in real time through anti-radiation temperature sensor array, micro-gravity accelerometer and atomic oxygen mass spectrometer at a preset sampling frequency;

[0015] S12: Use wavelet transform-Kalman filter hybrid algorithm for data preprocessing of key data to eliminate interference and align multi-source data;

[0016] S13: Extract three core parameters of periodic temperature difference, micro-gravity disturbance curve and material corrosion rate from the preprocessed key data;

[0017] S14: Establish a basic numerical model of welding process and microstructure change containing temperature difference sub-model, micro-gravity disturbance sub-model and atomic oxygen corrosion sub-model combined with experimental data.

[0018] The S2 step includes:

[0019] S21: Based on the basic numerical model, construct a space environment dynamic model, integrate the temperature difference cycle sub-model, the micro-gravity disturbance sub-model and the atomic oxygen corrosion sub-model to form a dynamic model framework describing the influence of space environment on the welding process;

[0020] S22: Construct a multi-scale coupling model based on the space environment dynamic model, realize the multi-physical field coupling of temperature field, stress field and material microstructure evolution in the welding process through thermal-mechanical coupling analysis, and establish the coupling mechanism of macro welding process and microstructure change;

[0021] S23: Systematically integrate the multi-scale coupling model with the intelligent optimization model and the virtual-real synchronization model to form a digital twin model with real-time simulation, parameter optimization and virtual-real mapping functions.

[0022] The S3 step includes:

[0023] S31: Use the digital twin model to establish the data mapping relationship between the digital model and the actual welding equipment through the virtual-real synchronization model;

[0024] S32: Use the multi-physical field coupling mechanism to calculate the temperature field, stress field and corrosion field data in the digital model in real time, and transfer them to the actual welding equipment through the shared memory pool;

[0025] S33: The actual welding equipment adjusts the welding parameters according to the received data and feeds back the real-time welding data to the shared memory pool for digital model updating, completing the establishment of a real-time data interaction mechanism.

[0026] The S4 step includes:

[0027] S41: Dynamically adjust the welding process parameters according to the real-time feedback data through the reinforcement learning algorithm in the intelligent optimization model;

[0028] S42: Use the reward function to evaluate the matching degree of the organizational changes in the welding process with the target prediction results, guiding the optimization and adjustment of the process parameters;

[0029] S43: Use a convolutional neural network to analyze thermal imaging data during the welding process, identify potential welding defects, and automatically correct the welding path and process parameters based on the identification results.

[0030] The S5 step includes:

[0031] S51: Establish a welding process data management database to store key data, adjusted process parameters, and organizational change data during the welding process;

[0032] S52: Analyze and mine historical data in the database, build a knowledge graph, and generate optimization suggestions;

[0033] S53: Based on historical data and optimization suggestions, continuously train the prediction accuracy of the optimized digital twin model and the parameter adjustment strategy of the intelligent optimization model.

[0034] The S22 step includes:

[0035] S221: Establish a thermal-mechanical coupling model, use finite element analysis methods, and calculate the dynamic evolution of temperature and stress fields during the welding process through coupled equation groups;

[0036] S222: Establish an austenite-martensite phase transformation model, use phase transformation equations based on the phase field method to predict microstructure evolution;

[0037] S223: Through thermal-mechanical-chemical coupling analysis, combined with the preset temperature difference cycle conditions, realize real-time data exchange of temperature field, stress field, phase change field and corrosion field, and establish a multi-scale coupling mechanism between macro and micro.

[0038] The S31 step includes:

[0039] S311: Obtain real-time data of extreme temperature difference cycles, microgravity disturbances, and atomic oxygen corrosion through an array of radiation-resistant temperature sensors, microgravity accelerometers, and atomic oxygen mass spectrometers;

[0040] S312: Use the data mapping engine to realize data synchronization between the digital model and the actual welding equipment through the OPC UA communication protocol, transmit the thermal-mechanical coupling calculation results and phase change prediction data;

[0041] S313: Through the feedback optimization module, the thermal-mechanical coupling optimization instructions and phase change control strategies in the digital twin model are transmitted to the actual welding equipment, forming a closed-loop control considering the extreme space environment.

[0042] Wherein, the S14 step includes:

[0043] S141: Establish an extreme temperature difference cycle submodel, and use a non-steady-state heat conduction equation to describe the heat conduction behavior of the welding material under a preset temperature difference cycle;

[0044] S142: Establish a microgravity disturbance submodel, and predict the influence of the microgravity environment on the welding pool shape and austenite-martensite phase change dynamics through an orbital dynamics equation;

[0045] S143: Establish an atomic oxygen corrosion submodel, and use a reaction kinetics equation to simulate the corrosion effect of atomic oxygen on the surface of the welding material, and combine the phase change model to predict the influence of corrosion on the evolution of the microstructure.

[0046] Wherein, the S12 step includes:

[0047] S121: Use wavelet transform to perform multi-scale denoising processing on key data containing extreme temperature difference cycles, and eliminate the sudden interference of solar flares;

[0048] S122: Use Kalman filtering to smooth the temperature field, microgravity and corrosion data after denoising, to ensure the data accuracy of thermal-mechanical coupling calculation and phase change prediction;

[0049] S123: Align the multi-source heterogeneous data through a space-time registration method, establish a unified time reference to support the synchronous calculation of thermal-mechanical coupling analysis and austenite-martensite phase change simulation.

[0050] Compared with the prior art, the present application has the following advantages:

[0051] A space environment welding digital twin method based on multi-scale dynamic coupling comprises the following steps: S1, collecting key data in a welding process, and combining experimental data to establish a basic numerical model of the welding process and organization change; S2, based on the basic numerical model, a digital twin model of the welding process is constructed by using a numerical simulation method, and the digital twin model integrates a space environment dynamic model, a multi-scale coupling model, an intelligent optimization model and a virtual-real synchronization model; S3, a real-time data interaction mechanism between the digital model and the actual welding equipment is established by using the virtual-real synchronization model in the digital twin model; S4, based on the feedback data obtained by the real-time data interaction mechanism, the intelligent optimization model in the digital twin model is used to automatically adjust the welding process parameters, so that the organization change of the welding process matches the target prediction result; S5, a welding process data management database is established to store the key data and the adjusted process parameters, and the prediction accuracy of the optimization digital twin model is continuously trained based on the historical data in the database. The space dynamic environment (such as-150℃~200℃ temperature difference cycle) and material phase change coupling effect which cannot be accurately simulated by the prior art are filled.

[0052] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or can be learned by practice of the present application.

[0053] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation on the present application. In the drawings:

[0055] Figure 1 A flowchart of a space environment welding digital twin method based on multi-scale dynamic coupling in an embodiment of the present application;

[0056] Figure 2 A flowchart of establishing a basic numerical model of the welding process and organization change in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The preferred embodiments of the present application will be described below in combination with the drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not limit the present application.

[0058] The embodiment of the present application provides a space environment welding digital twin method based on multi-scale dynamic coupling as shown in Figure 1 The embodiment of the present application provides a space environment welding digital twin method based on multi-scale dynamic coupling as shown in

[0059] S1: Collect key data during the welding process, and establish a basic numerical model of the welding process and organizational changes based on experimental data;

[0060] S2: Based on the basic numerical model, a digital twin model of the welding process is constructed using numerical simulation methods. The digital twin model integrates a spatial environment dynamic model, a multi-scale coupling model, an intelligent optimization model, and a virtual-real synchronization model.

[0061] S3: Using the virtual-real synchronization model in the digital twin model, a real-time data interaction mechanism between the digital model and the actual welding equipment is established.

[0062] S4: Based on the feedback data obtained through the real-time data interaction mechanism, the intelligent optimization model in the digital twin model automatically adjusts the welding process parameters, so that the organizational changes in the welding process match the target prediction results.

[0063] S5: Establish a welding process data management database to store key data and adjusted process parameters, and continuously train the prediction accuracy of the optimized digital twin model based on historical data in the database.

[0064] The working principle of the above technical solution is as follows: S1: The system collects key parameters in the space welding environment in real time through special equipment such as an anti-radiation temperature sensor array, a micro-gravity accelerometer, and an atomic oxygen mass spectrometer. The sampling frequency is up to 100Hz, ensuring the complete acquisition of data such as extreme temperature differences of-150℃ to 200℃ and 10 -6 g micro-gravity disturbances. The anti-radiation temperature sensor array is a temperature measurement device that can work normally in a strong radiation environment; the micro-gravity accelerometer is used to measure small gravity changes in a near-zero gravity state; and the atomic oxygen mass spectrometer is used to detect the active atomic oxygen concentration in the upper atmosphere. The raw data collected are preprocessed by a wavelet transform-Kalman filter hybrid algorithm to eliminate sudden disturbances such as solar flares, and are aligned by a time-space registration module to synchronize the multi-source heterogeneous data with a time synchronization accuracy of within 1μs. Based on the processed data, combined with experimental data and numerical simulation results, a basic numerical model is established to describe key physical phenomena such as temperature evolution, material organizational changes, and stress distribution during the welding process.

[0065] S2: The system constructs a digital twin model containing four core sub-models. The space environment dynamic model includes a temperature difference cycle sub-model, a microgravity disturbance sub-model, and an atomic oxygen corrosion sub-model, which are used to simulate the periodic temperature changes caused by day-night alternation, the influence of microgravity environment on material fluidity, and the oxidation corrosion effect of atomic oxygen on material surface in orbit operation. The multi-scale coupling model establishes a thermal-mechanical coupling model at the macro scale through finite element analysis method to calculate the dynamic evolution of temperature field and stress field, and at the same time, uses phase field simulation to predict the austenite-martensite phase transition process at the micro scale, where austenite is a face-centered cubic crystal structure stable at high temperature, and martensite is a body-centered cubic or body-centered tetragonal crystal structure formed by rapid cooling. The intelligent optimization model integrates reinforcement learning algorithm and convolutional neural network, the reinforcement learning algorithm dynamically adjusts the welding current, voltage and speed parameters by designing reward function, and the convolutional neural network analyzes infrared thermal imaging to identify potential welding defects. The virtual-real synchronization model establishes real-time communication bridge between digital model and physical equipment through OPC UA protocol, which is an industrial automation standard communication protocol supporting cross-platform device interconnection.

[0066] S3: The system uses the data mapping engine in the virtual-real synchronization model to realize the bidirectional real-time data interaction between the digital twin model and the actual welding equipment through the OPC UA protocol. The real-time data acquisition module obtains real-time operation parameters such as temperature, pressure, position, current from various sensors of the physical welding equipment, and the data transmission delay is controlled within milliseconds. The data mapping engine converts the measured data of the physical equipment into a standardized format recognizable by the digital model, and at the same time establishes a data quality evaluation mechanism to automatically identify and eliminate abnormal data. The feedback optimization module transmits the optimization instructions calculated by the digital twin model to the control system of the welding equipment through the actuator interface, forming a closed-loop control circuit. The entire data interaction process ensures the consistency of the virtual world and the physical world through the space-time synchronization algorithm, realizing the true sense of "virtual-real synchronization".

[0067] S4: Based on the real-time collected feedback data, the system automatically adjusts the welding process parameters through the intelligent optimization algorithm in the digital twin model, so that the actual welding process organization changes match the target prediction results. The reinforcement learning algorithm dynamically optimizes the key parameters such as welding current, voltage and welding speed according to the current welding state and environmental conditions. The reward function of the algorithm considers multiple quality indicators such as temperature deviation, residual stress and welding defect rate. The convolutional neural network analyzes the infrared thermal imaging images of the welding process in real time, identifies potential defects such as pores and cracks, and automatically adjusts the welding path and process parameters for correction once abnormal patterns are detected. The multi-scale coupled model simultaneously calculates the macro temperature field, stress field distribution and microstructure phase change process, providing comprehensive physical basis for parameter optimization. The entire optimization process adopts an adaptive control strategy, dynamically adjusting the parameter weights of the optimization algorithm according to the real-time evaluation results of the welding quality.

[0068] S5: The system establishes a special welding process data management database, which includes three core components: experimental data storage unit, simulation result storage unit and knowledge graph construction module. The experimental data storage unit saves the original data of ground and space welding tests, including sensor measurement values, process parameter settings, welding quality evaluation results, etc.; the simulation result storage unit archives the calculation results of numerical simulation, including temperature field evolution, stress distribution, organization change, etc.; the knowledge graph construction module analyzes the correlation rules between historical data through data mining technology and automatically generates process optimization suggestions. The database adopts a distributed storage architecture, supporting efficient storage and retrieval of large-scale data. Based on the historical data accumulated in the database, the system uses machine learning algorithms to continuously train and optimize the prediction accuracy of the digital twin model, including updating neural network weights, adjusting physical model parameters and improving optimization algorithm strategies. Through this continuous learning mechanism, the digital twin model can continuously adapt to new welding conditions and process requirements, improving prediction accuracy and optimization effect.

[0069] The beneficial effects of the above technical solutions are that the welding digital twin technology considering multi-scale coupled model in the welding process can realize intelligent evaluation and optimization of the welding process, improving the welding quality and efficiency. This will bring important technical breakthroughs to the development of welding industry, promoting the development of welding process towards intelligence and efficiency.

[0070] In another embodiment, as shown in Figure 2 S1 step includes:

[0071] S11: Collect key data of temperature field, microgravity disturbance and material corrosion in space welding process in real time through anti-radiation temperature sensor array, microgravity accelerometer and atomic oxygen mass spectrometer with preset sampling frequency;

[0072] S12: adopt wavelet transform-Kalman filter hybrid algorithm to preprocess the key data, eliminate interference and align multi-source data;

[0073] S13: extract three types of core parameters of periodic temperature difference, microgravity disturbance curve and material corrosion rate from the preprocessed key data;

[0074] S14: combined with experimental data to establish a basic numerical model of welding process and microstructure change containing temperature difference sub-model, microgravity disturbance sub-model and atomic oxygen corrosion sub-model.

[0075] The working principle of the above technical scheme is: S11: real-time collection of key environmental data in space welding process through special sensor array; wherein, the extreme temperature difference of-150℃-200℃ is captured by using anti-radiation temperature sensor array, the gravity disturbance of 10 -6 g level is monitored by microgravity accelerometer, and the oxidation corrosion degree of material surface is measured by atomic oxygen mass spectrometer; the preset sampling frequency is 100Hz, which ensures that the dynamic change characteristics of space environment can be recorded completely;

[0076] S12: adopt wavelet transform-Kalman filter hybrid algorithm to preprocess the key data; wherein, wavelet transform is used for multi-scale denoising processing, which can effectively eliminate the influence of sudden electromagnetic interference such as solar flare on sensor data; Kalman filter is used for smoothing processing of temperature field, microgravity and corrosion data after denoising, which can improve the data accuracy; time synchronization of multi-source heterogeneous data is realized by time and space registration method, and the synchronization accuracy is controlled within 1μs;

[0077] S13: extract core environmental parameters from preprocessed key data; wherein, the three types of core parameters include: periodic temperature difference function ΔT(t) reflects the influence of day and night alternation and orbit β angle change, microgravity disturbance curve G(t) describes the change of gravity field caused by orbit dynamics, and material corrosion rate O(t) quantifies the erosion degree of atomic oxygen to material surface; these parameters constitute environmental feature tensor E(t)=[ΔT(t),G(t),O(t)];

[0078] S14: combined with experimental data to establish a basic numerical model containing three sub-models; wherein, the temperature difference sub-model adopts the following non-steady-state heat conduction equation to describe the heat conduction behavior under complex temperature difference cycle:

[0079]

[0080] wherein ρ is the density of material, c p is the specific heat capacity, k is the thermal conductivity, Q r is the radiation heat source term;

[0081] The microgravity disturbance sub-model predicts the influence of microgravity on the welding process through an orbital dynamics equation:

[0082]

[0083] where G is the gravitational constant, M is the mass of the earth, R is the orbital radius, ω is the orbital angular velocity, and g0 is the standard gravity acceleration;

[0084] The atomic oxygen corrosion sub-model uses a reaction kinetics equation to establish the relationship between the corrosion rate and the environmental parameters:

[0085]

[0086] where R is the corrosion rate, k is the reaction rate constant, F is the atomic oxygen flux, E is the activation energy, R is the gas constant, and T is the temperature. c c AO a

[0087] The beneficial effects of the above technical solution are that the blank of the inability of the prior art to accurately simulate the coupling effect of the space dynamic environment (such as -150℃-200℃ temperature difference cycle) and material phase change can be filled.

[0088] In another embodiment, the S2 step comprises:

[0089] S21: constructing a space environment dynamic model based on a basic numerical model, integrating the temperature difference cycle sub-model, the microgravity disturbance sub-model, and the atomic oxygen corrosion sub-model to form a dynamic model framework describing the influence of the space environment on the welding process;

[0090] S22: constructing a multi-scale coupling model based on the space environment dynamic model, realizing the multi-physical field coupling of the temperature field, the stress field, and the material organization evolution in the welding process through thermal-mechanical coupling analysis, and establishing the coupling mechanism of the macro welding process and the micro organization change;

[0091] S23: systemically integrating the multi-scale coupling model with the intelligent optimization model and the virtual-real synchronization model to form a digital twin model with real-time simulation, parameter optimization, and virtual-real mapping functions.

[0092] The working principle of the above technical solution is that S21: constructing a space environment dynamic model based on a basic numerical model; wherein the temperature difference cycle sub-model, the microgravity disturbance sub-model, and the atomic oxygen corrosion sub-model are systemically integrated to form a unified space environment dynamic model framework; the framework realizes data interaction between the sub-models through a shared memory pool and can comprehensively describe the coupling influence of -150℃-200℃ temperature difference cycle, microgravity disturbance, and atomic oxygen corrosion on the welding process;

[0093] ​​​​S22: Construct a multi-scale coupling model based on the spatial environment dynamic model, and realize multi-physical field coupling through thermal-mechanical coupling analysis; wherein the multi-scale coupling model uses the finite element analysis method to take the welding heat source as the heat input, and establishes a thermal-mechanical coupling model:

[0094] [K T ]{T}={Q},[K S ]{σ}={F}

[0095] wherein [K T ] is a thermal stiffness matrix, [K S ] is a structural stiffness matrix, {T} is a temperature field, {σ} is a stress field, {Q} is a radiation heat source term, and {F} is an external force;

[0096] The corrosion field data is obtained through a corrosion rate calculation formula:

[0097]

[0098] wherein R c is the corrosion rate, k c is the reaction rate constant, F AO is the atomic oxygen flux, E a is the activation energy; the calculation results realize real-time data exchange of the temperature field, the stress field and the corrosion field through a shared memory pool, and the data interaction of each sub-model is realized through the shared memory pool, and a coupling time step adaptive adjustment strategy is set;

[0099] The coupling of the macro welding process and the microstructure change is realized through a phase field method, and an austenite-martensite phase transition model is established:

[0100]

[0101] wherein is a phase field variable describing the material organization state, M is the mobility, and F is a free energy function including chemical free energy, elastic strain energy and interface energy; the multi-physical field coupling mechanism realizes real-time data exchange of the temperature field, the stress field and the corrosion field through a coupling time step adaptive adjustment strategy, and predicts the dynamic change of the microstructure such as grain growth and phase transition process in the welding process;

[0102] S23: System integration of the multi-scale coupling model, the intelligent optimization model and the virtual-real synchronization model; wherein the system integration realizes seamless connection between the models through standardized data interfaces and communication protocols; a complete digital twin model with real-time simulation, parameter optimization and virtual-real mapping functions is formed; the model can respond to the state change of the physical welding process in real time, and provide predictive process optimization suggestions.

[0103] The beneficial effects of the above technical solution are that the system integrated digital twin model has real-time simulation, parameter optimization and virtual-real mapping functions, and can realize intelligent evaluation and optimal control of the welding process in a complex space environment.

[0104] In another embodiment, the S3 step comprises:

[0105] S31: using a digital twin model, establishing a data mapping relationship between the digital model and the actual welding equipment through a virtual-real synchronization model;

[0106] S32: using a multi-physics field coupling mechanism, real-time calculation of temperature field, stress field and corrosion field data in the digital model, and passing to the actual welding equipment through a shared memory pool;

[0107] S33: the actual welding equipment adjusts the welding parameters according to the received data, and feeds back the real-time welding data to the shared memory pool for digital model updating, and completes the establishment of the real-time data interaction mechanism.

[0108] The working principle of the above technical solution is that S31: a virtual-real synchronization model is used to establish a data mapping relationship between the digital model and the actual welding equipment; wherein the data mapping relationship is established through a data mapping engine, which defines the correspondence between the virtual sensors in the digital space and the actual sensors in the physical space; at the same time, the control mapping of the virtual actuator and the physical actuator is established to ensure that the calculation results of the digital model can be accurately transmitted to the physical equipment;

[0109] S32: using a multi-physics field coupling mechanism to real-time calculate and transmit field data; wherein the multi-physics field coupling mechanism solves the distribution state of the temperature field, stress field and corrosion field in real time, and the calculation results are transmitted to the actual welding equipment through a shared memory pool; the shared memory pool uses high-speed data buffering technology to ensure the synchronous updating and fast access of multi-physics field data;

[0110] S33: the actual welding equipment adjusts the parameters according to the received data and feeds back the real-time data; wherein the actual welding equipment automatically adjusts the process parameters such as welding current, voltage, speed, etc. according to the received temperature field, stress field data; at the same time, the actual running state of the equipment, the sensor measurement data is fed back to the shared memory pool in real time for digital model updating and correction, forming a complete real-time data interaction closed loop.

[0111] The beneficial effects of the above technical solution are that the real-time welding data including actual temperature distribution, stress change and material organization evolution information is fed back to the shared memory pool for digital model updating, forming a closed-loop control system, and realizing intelligent optimization of welding parameters.

[0112] In another embodiment, the S4 step comprises:

[0113] S41: The welding process parameters are dynamically adjusted based on real-time feedback data through the reinforcement learning algorithm in the intelligent optimization model.

[0114] S42: Use reward functions to evaluate the degree of matching between the microstructure changes during the welding process and the target prediction results, and guide the optimization and adjustment of process parameters;

[0115] S43: Uses convolutional neural networks to analyze thermal imaging data during the welding process, identify potential welding defects, and automatically correct the welding path and process parameters based on the identification results.

[0116] The working principle of the above technical solution is as follows: S41: The welding process parameters are dynamically adjusted through a reinforcement learning algorithm; wherein, the reinforcement learning algorithm takes the current welding state as input and outputs the adjustment amount of welding current, voltage and speed through a policy network; the algorithm learns the optimal parameter adjustment strategy through interaction with the environment and can adapt to the complex and ever-changing spatial welding environment.

[0117] S42: Utilize a reward function to evaluate the degree of matching between the welding process and the target; whereby, the reward function is designed as follows:

[0118] R = -(w1·ΔT + w2·σ) r +w3·D f )

[0119] Where ΔT is the temperature deviation, σ r For residual stress, D f The welding defect rate is represented by w1, w2, and w3, which are weighting parameters.

[0120] The reward function comprehensively considers three key indicators: temperature deviation, residual stress, and welding defect rate; the weight parameters w1, w2, and w3 are adjusted according to specific welding quality requirements; the calculation results of the reward function guide the strategy update of the reinforcement learning algorithm, thereby achieving continuous optimization of process parameters.

[0121] S43: The system uses a convolutional neural network to analyze thermal imaging data and automatically correct process parameters. The convolutional neural network performs real-time analysis of infrared thermal images during the welding process to identify potential welding defects such as porosity and cracks. Based on the defect identification results, the system automatically calculates the optimal welding path correction scheme and process parameter adjustment strategy to achieve adaptive control of the welding process.

[0122] The beneficial effects of the above technical solution are as follows: the execution of parameter adjustment aims to meet the welding quality requirements in the space environment. The execution results are then fed back into the reinforcement learning algorithm through the feedback optimization module to continuously optimize the decision-making strategy, ensuring that the organizational changes in the welding process are highly matched with the prediction results of the digital twin model, and ultimately realizing intelligent evaluation and dynamic optimization of welding quality in the space environment.

[0123] In another embodiment, the S5 step comprises:

[0124] S51: Establish a welding process data management database to store key data, adjusted process parameters, and microstructure change data during the welding process;

[0125] S52: Analyze and mine historical data in the database, build a knowledge graph, and generate optimization suggestions;

[0126] S53: Based on historical data and optimization suggestions, continuously train the prediction accuracy of the optimized digital twin model and the parameter adjustment strategy of the intelligent optimization model.

[0127] The working principle of the above technical solution is as follows: S51: Establish a comprehensive welding process data management database; the database adopts a hierarchical storage architecture, including a real-time data cache layer, a historical data storage layer, and a knowledge data management layer; the storage content covers key environmental data, optimized process parameters, microstructure change data during the welding process, etc.; the database supports high-concurrency access and fast retrieval of large data volumes;

[0128] S52: Analyze and mine historical data in the database and build a knowledge graph; through data mining algorithms, analyze the correlation between welding parameters, environmental conditions, and welding quality; the knowledge graph construction module converts the mined rules into structured knowledge representation, generating process optimization suggestions for different welding conditions; the knowledge graph supports semantic query and reasoning, providing intelligent support for welding process decision-making;

[0129] S53: Continuously train the optimized digital twin model based on historical data; use accumulated historical data to retrain the prediction algorithm of the digital twin model to improve the prediction accuracy and generalization ability of the model; at the same time, optimize the parameter adjustment strategy in the intelligent optimization model to better adapt to different welding scenarios; form a data-driven model continuous improvement mechanism.

[0130] The beneficial effects of the above technical solution are: the purpose of continuous optimization is to enable the digital twin model to more accurately predict the microstructure changes during the welding process in space, and the intelligent optimization algorithm to better adapt to complex space environments and welding conditions.

[0131] In another embodiment, the S22 step comprises:

[0132] S221: Establish a thermal-mechanical coupling model, use finite element analysis methods, and calculate the dynamic evolution of the temperature field and stress field during the welding process through coupled equation sets;

[0133] S222: Establish an austenite-martensite phase transformation model, use the phase transformation equation based on the phase field method to predict microstructure evolution;

[0134] S223: Real-time data exchange between temperature field, stress field, phase change field and corrosion field is realized through thermal-mechanical-chemical coupling analysis combined with preset temperature difference cycle conditions, and a macro-micro multi-scale coupling mechanism is established.

[0135] The working principle of the above technical solution is as follows: S221: A thermal-mechanical coupling model is established for dynamic evolution calculation; wherein, by solving the coupled heat conduction equation and structural mechanics equation, the space-time distribution of temperature field and stress field during welding is calculated by using finite element analysis method; the coupling solution considers the change of material thermal physical parameters with temperature and the reaction of thermal stress on temperature field;

[0136] S222: An austenite-martensite phase change model is established to predict microstructure evolution; wherein, the phase change model is constructed based on phase field method:

[0137]

[0138] Wherein, the phase field variable Describes the material organization state, M is the mobility, and the free energy function F includes chemical free energy, elastic strain energy and interface energy; by solving the phase field equation, the microstructure changes such as grain growth and phase change during welding are predicted;

[0139] S223: A macro-micro multi-scale coupling mechanism is established through multi-physical field coupling analysis; wherein, the real-time data exchange between temperature field, stress field, phase change field and corrosion field is realized combined with preset temperature difference cycle conditions; the multi-scale coupling mechanism transmits the macro temperature and stress information to the micro phase change model through the scale bridging algorithm, and at the same time, the influence of microstructure change on material performance is fed back to the macro model.

[0140] The beneficial effects of the above technical solution are: by setting the coupling time step adaptive adjustment strategy, the real-time data exchange between temperature field from step one thermal-mechanical coupling model, stress field from structural mechanics calculation, phase change field from step two phase field model, and corrosion field from atomic oxygen corrosion sub-model is realized, thereby establishing a multi-scale dynamic coupling calculation framework from macro welding process to microstructure evolution.

[0141] In another embodiment, the S31 step includes:

[0142] S311: Real-time data of extreme temperature difference cycle, microgravity disturbance and atomic oxygen corrosion is obtained through the anti-radiation temperature sensor array, microgravity accelerometer and atomic oxygen mass spectrometer;

[0143] S312: The data mapping engine is used to realize data synchronization between digital model and actual welding equipment through OPC UA communication protocol, and to transmit thermal-mechanical coupling calculation results and phase change prediction data.

[0144] S313: transmitting the thermal-mechanical coupling optimization instructions and the phase change control strategy in the digital twin model to the actual welding equipment through the feedback optimization module to form a closed-loop control considering the extreme space environment.

[0145] The working principle of the above technical solution is: S311: obtaining real-time data of the space environment through a special sensor; wherein, an array of radiation-resistant temperature sensors measures extreme temperature difference cycle data, a microgravity accelerometer monitors gravity disturbance information, and an atomic oxygen mass spectrometer detects the surface corrosion condition of the material; the sensor data is transmitted to a data mapping engine in real time for processing and format conversion;

[0146] S312: realizing data synchronization between the digital model and the actual equipment by using the data mapping engine; wherein, a standardized data exchange channel is established through the OPC UA communication protocol to transmit the thermal-mechanical coupling calculation results and the phase change prediction data; the data mapping engine is responsible for the conversion and synchronization between different data formats, ensuring the data consistency between the digital model and the physical equipment;

[0147] S313: forming a closed-loop control considering the extreme space environment through the feedback optimization module; wherein, the feedback optimization module transmits the thermal-mechanical coupling optimization instructions and the phase change control strategy calculated by the digital twin model to the actual welding equipment; the equipment feeds back the results to the digital model after executing the optimization instructions, forming a complete closed-loop control system, and realizing self-adaptive control of the extreme space environment conditions.

[0148] The beneficial effects of the above technical solution are: the closed-loop control continuously monitors the deviation between the actual welding effect and the prediction result of the digital model, dynamically corrects the process parameters such as welding current, voltage and speed, and ensures the stability and controllability of the welding quality in the extreme space environment.

[0149] In another embodiment, the S14 step includes:

[0150] S141: establishing an extreme temperature difference cycle sub-model to describe the heat conduction behavior of the welding material under a preset temperature difference cycle using a non-steady-state heat conduction equation;

[0151] S142: establishing a microgravity disturbance sub-model to predict the influence of the microgravity environment on the welding pool shape and austenite-martensite phase change dynamics through an orbital dynamics equation;

[0152] S143: establishing an atomic oxygen corrosion sub-model to simulate the corrosion effect of atomic oxygen on the surface of the welding material using a reaction kinetics equation, and predicting the influence of corrosion on the evolution of the microstructure in combination with the phase change model.

[0153] The working principle of the above technical solution is: S141: establishing an extreme temperature difference cycle sub-model to describe the heat conduction behavior;

[0154] Where, the non-steady-state heat conduction equation is used to describe the heat transfer process of welding material under the temperature difference cycle of-150℃-200℃:

[0155]

[0156] Where, ρ is the material density, c p is the specific heat capacity, k is the thermal conductivity, Q r is the radiation heat source term.

[0157] Since there is no air conduction in the space environment, the radiation heat transfer equation is introduced to calculate the heat exchange, that is:

[0158]

[0159] Where, ε is the material surface emissivity, σ is the Stefan-Boltzmann constant, is the background temperature; the microgravity perturbation model uses the following formula to calculate the orbital microgravity effect:

[0160] S142: Establish a microgravity perturbation model to predict the influence on the welding process; wherein the orbital dynamics equation

[0161]

[0162] Where, G is the gravitational constant, M is the mass of the earth, R is the orbital radius, ω is the orbital angular velocity, g0 is the standard gravity acceleration;

[0163] The model predicts the influence of microgravity on the welding pool shape, material flow and austenite-martensite phase transformation dynamics;

[0164] S143: Establish an atomic oxygen corrosion sub-model to simulate the corrosion effect; wherein the atomic oxygen corrosion sub-model uses the following chemical reaction kinetics equation to describe the corrosion process:

[0165]

[0166] Where, R c is the corrosion rate, k c is the reaction rate constant, F AO is the atomic oxygen flux, E a is the activation energy, R is the gas constant, T is the temperature; the three sub-models realize real-time data interaction through a shared memory pool, forming a complete space environment welding process numerical simulation foundation. Combined with the phase transformation model, the influence of corrosion on material microstructure evolution is predicted, and corrosion field data is provided for multi-physical field coupling analysis.

[0167] The beneficial effects of the above technical solution are: the model combines the phase change model to analyze the influence of corrosion on material organization evolution, predicts the corrosion rate and the thickness change of the oxide layer, and provides accurate corrosion field data input for multi-physical field coupling analysis.

[0168] In another embodiment, the S12 step comprises:

[0169] S121: multi-scale denoising processing of key data containing extreme temperature difference cycles is performed by using wavelet transform to eliminate the burst interference of solar flares;

[0170] S122: the temperature field, microgravity and corrosion data after denoising are smoothed by using Kalman filtering to ensure the data accuracy of thermal-mechanical coupling calculation and phase change prediction;

[0171] S123: multi-source heterogeneous data are aligned by using a space-time registration method, and a unified time reference is established to support the synchronous calculation of thermal-mechanical coupling analysis and austenite-martensite phase change simulation.

[0172] The working principle of the above technical solution is: S121: multi-scale denoising processing is performed by using wavelet transform; wherein, the key data mainly come from the real-time collection of the anti-radiation temperature sensor array, the microgravity accelerometer and the atomic oxygen mass spectrometer, the sampling frequency reaches 100Hz, and the extreme temperature difference cycle data of-150℃-200℃, the microgravity disturbance data of 10^-6g level and the atomic oxygen corrosion related data are covered; the wavelet transform is a multi-resolution time-frequency analysis method, which can decompose signals in different time scales and frequency scales, effectively identify and separate noise interference of different frequency components; the solar flare is an explosive phenomenon occurring on the surface of the sun, which can produce strong electromagnetic radiation and particle flow, causing burst interference to electronic devices and sensors in the space environment; through the multi-scale decomposition characteristics of wavelet transform, the high-frequency burst interference signal generated by the solar flare can be separated from the low-frequency periodic signal of the temperature difference cycle, ensuring the accuracy of the environmental parameters such as temperature difference function ΔT(t), microgravity curve G(t) and corrosion rate O(t);

[0173] S122: data smoothing processing is performed by using Kalman filtering; wherein, the Kalman filtering is a recursive filtering algorithm based on a state space model, which can effectively process measurement data containing noise by using a prediction-correction mechanism to optimally estimate the state of a dynamic system; the temperature field data is described based on the heat conduction-radiation coupling equation:

[0174]

[0175] wherein, ρ is the density of the material, c p is the specific heat capacity, k is the thermal conductivity, Q rFor the radiation heat source term, the radiation heat transfer equation is introduced to calculate the heat exchange due to the absence of air conduction in the space environment, i.e.,

[0176]

[0177] where ε is the material surface emissivity, σ is the Stefan-Boltzmann constant, is the background temperature; the orbit microgravity effect is calculated by the microgravity perturbation model using the following formula:

[0178]

[0179] where G is the gravitational constant, M is the Earth mass, R is the orbit radius, ω is the orbit angular velocity, g0 is the standard gravity acceleration; the atomic oxygen corrosion process is described by the chemical reaction kinetics equation of the atomic oxygen corrosion sub-model as follows:

[0180]

[0181] where R c is the corrosion rate, k c is the reaction rate constant, F AO is the atomic oxygen flux, E a is the activation energy, R is the gas constant, and T is the temperature; the real-time data interaction of the three sub-models is realized through a shared memory pool, forming a complete space environment welding process numerical simulation foundation. Through the state estimation and error covariance updating mechanism of Kalman filtering, the heat-force coupling calculation model is ensured:

[0182] [K T ]{T}={Q},[K S ]{σ}={F}

[0183] where [K T ] is the thermal conductivity stiffness matrix, [K S ] is the structural stiffness matrix, {T} is the temperature field, {σ} is the stress field, {Q} is the radiation heat source term, and {F} is the external force; the coupling of the macro welding process and the microstructure change is realized by the phase field method, and an austenite-martensite phase transition model is established:

[0184]

[0185] where is the phase field variable describing the material organization state, M is the mobility, and F is the free energy function including the chemical free energy, the elastic strain energy, and the interface energy; the multi-physical field coupling mechanism realizes the real-time data exchange of the temperature field, the stress field, and the corrosion field through the setting of the coupling time step adaptive adjustment strategy, and predicts the dynamic changes of the microstructure such as grain growth and phase transition process in the welding process;

[0186] S123: aligning multi-source data by a spatio-temporal registration method; wherein the spatio-temporal registration refers to a technique of accurately aligning multi-source heterogeneous data from different sensors, different sampling times and spatial positions in time and space dimensions; the multi-source heterogeneous data includes thermal field data of a temperature sensor array, micro-gravity data of an accelerometer, atomic oxygen data of a mass spectrometer and the like, which have different sampling frequencies, data formats and time stamps; the registration method adopts a time synchronization technique based on feature matching and interpolation algorithm to unify the time stamps of the sensor data to a same reference time system, and the synchronization accuracy is controlled within 1 mu s; the establishment of the unified time reference ensures the time consistency of each component in the environmental feature tensor E(t) = [Delta T(t), G(t), O(t)].

[0187] The above technical solution has the beneficial effects that: it provides a synchronous calculation basis for subsequent thermal-mechanical coupling analysis and microstructure phase transformation simulation, so that the temperature field, stress field and corrosion field can be coupled and solved at the same time node, and real-time data exchange and collaborative calculation of multi-physical fields are realized.

[0188] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application.

Claims

1. A multi-scale dynamic coupling based spatial environment welding digital twin method, characterized in that, Comprise: S1: Collect key data in the welding process, and establish a basic numerical model of the welding process and organizational change combined with experimental data; S2: Based on the basic numerical model, a digital twin model of the welding process is constructed using numerical simulation methods, which integrates a spatial environment dynamic model, a multi-scale coupling model, an intelligent optimization model, and a virtual-real synchronization model; S3: Using the virtual-real synchronization model in the digital twin model, a real-time data interaction mechanism between the digital model and the actual welding equipment is established; S4: Based on the feedback data obtained through the real-time data interaction mechanism, the intelligent optimization model in the digital twin model automatically adjusts the welding process parameters, so that the organizational change in the welding process matches the target prediction result; S5: Establish a welding process data management database to store key data and adjusted process parameters, and continuously train the prediction accuracy of the optimized digital twin model based on historical data in the database.

2. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 1, wherein, S1 step includes: S11: Collect key data of temperature field, micro-gravity disturbance and material corrosion in space welding process in real time through anti-radiation temperature sensor array, micro-gravity accelerometer and atomic oxygen mass spectrometer with preset sampling frequency; S12: Use wavelet transform-Kalman filter hybrid algorithm for data preprocessing of key data to eliminate interference and align multi-source data; S13: Extract three types of core parameters, periodic temperature difference, micro-gravity disturbance curve and material corrosion rate, from the preprocessed key data; S14: Combine experimental data to establish a basic numerical model of the welding process and organizational change including temperature difference sub-model, micro-gravity disturbance sub-model and atomic oxygen corrosion sub-model.

3. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 1, wherein, S2 step includes: S21: Based on the basic numerical model, a spatial environment dynamic model is constructed, and the temperature difference cycle sub-model, the micro-gravity disturbance sub-model and the atomic oxygen corrosion sub-model are integrated to form a dynamic model framework describing the influence of the space environment on the welding process; S22: Based on the spatial environment dynamic model, a multi-scale coupling model is constructed, and through thermal-mechanical coupling analysis, the multi-physical field coupling of temperature field, stress field and material organization evolution in the welding process is realized, and the coupling mechanism of macro welding process and micro organizational change is established; S23: Systematically integrate the multi-scale coupling model with the intelligent optimization model and the virtual-real synchronization model to form a digital twin model with real-time simulation, parameter optimization and virtual-real mapping functions.

4. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 1, wherein, S3 step includes: S31: Use the digital twin model to establish the data mapping relationship between the digital model and the actual welding equipment through the virtual-real synchronization model; S32: Use the multi-physical field coupling mechanism to calculate the temperature field, stress field and corrosion field data in the digital model in real time, and pass them to the actual welding equipment through the shared memory pool; S33: The actual welding equipment adjusts the welding parameters according to the received data, and feeds back the real-time welding data to the shared memory pool for digital model update, completing the establishment of the real-time data interaction mechanism.

5. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 1, wherein, S4 step includes: S41: Dynamically adjust the welding process parameters according to the real-time feedback data through the reinforcement learning algorithm in the intelligent optimization model; S42: Evaluate the matching degree of the microstructure changes in the welding process with the target prediction results using the reward function, and guide the optimization and adjustment of the process parameters; S43: Use a convolutional neural network to analyze thermal imaging data during welding to identify potential welding defects, and automatically correct the welding path and process parameters based on the identification results.

6. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 1, wherein, S5 steps include: S51: Establish a welding process data management database to store key data, adjusted process parameters, and microstructure change data during welding; S52: Analyze and mine historical data in the database to build a knowledge graph and generate optimization suggestions; S53: Based on historical data and optimization suggestions, continuously train the prediction accuracy of the optimized digital twin model and the parameter adjustment strategy of the intelligent optimization model.

7. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 3, wherein, S22 steps include: S221: Establish a thermal-mechanical coupling model, use finite element analysis methods, and calculate the dynamic evolution of temperature and stress fields during welding through coupled equation groups; S222: Establish an austenite-martensite phase change model, use phase change equations based on the phase field method to predict microstructure evolution; S223: Through thermal-mechanical-chemical coupling analysis, combined with preset temperature difference cycle conditions, realize real-time data exchange of temperature field, stress field, phase change field and corrosion field, and establish a multi-scale coupling mechanism between macro and micro.

8. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 4, wherein, S31 steps include: S311: Obtain real-time data of extreme temperature difference cycles, microgravity disturbances, and atomic oxygen corrosion through an array of radiation-resistant temperature sensors, microgravity accelerometers, and atomic oxygen mass spectrometers; S312: Use a data mapping engine to achieve data synchronization between the digital model and the actual welding equipment through the OPC UA communication protocol, and transmit thermal-mechanical coupling calculation results and phase change prediction data; S313: Through the feedback optimization module, transmit the thermal-mechanical coupling optimization instructions and phase change control strategies in the digital twin model to the actual welding equipment, forming a closed-loop control considering the extreme space environment.

9. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 2, wherein, S14 steps include: S141: Establish an extreme temperature difference cycle sub-model, use a non-steady-state heat conduction equation to describe the heat conduction behavior of welding materials under the preset temperature difference cycle; S142: Establish a microgravity disturbance sub-model, predict the influence of microgravity environment on the shape of welding pool and the dynamics of austenite-martensite phase change through orbital dynamics equations; S143: Establish an atomic oxygen corrosion sub-model, use reaction kinetics equations to simulate the corrosion effect of atomic oxygen on the surface of welding materials, and predict the influence of corrosion on microstructure evolution in combination with the phase change model.

10. The multi-scale dynamic coupling based spatial environment welding digital twin method of claim 2, wherein, S12 steps include: S121: Use wavelet transform to perform multi-scale denoising processing on key data containing extreme temperature difference cycles, eliminating the sudden interference of solar flares; S122: Use Kalman filtering to smooth the temperature field, microgravity, and corrosion data after denoising, ensuring the data accuracy of thermal-mechanical coupling calculation and phase change prediction; S123: Align multi-source heterogeneous data through a spatio-temporal registration method, establish a unified time reference to support synchronous calculation of thermal-mechanical coupling analysis and austenite-martensite phase change simulation.

Images