3157 results about "Finite element simulation" patented technology

A method of constructing a digital twin physical field of a computer numerical control machine tool with double order reduction is provided. A physical field finite element simulation sample data set in a working state sampling space has an order preliminarily reduced to sparse grid node data via an improved K Nearest Neighbor (KNN) algorithm, so that the number of point sets is kept within the real-time rendering capability range of graphic rendering software. A digital twin physical field proxy model is trained using a radial basis function (RBF) to realize reconstruction of the physical field. The proxy model is iteratively optimized using a genetic algorithm to solve the problem of deviation between a proxy physical field model and a real physical model. Finally, the proxy model is deployed to a digital twin system, and the physical field distribution is solved in real time.

The invention relates to the technical field of water photovoltaic flexible support pile foundation construction data processing, in particular to a process for a water photovoltaic flexible support pile foundation, which comprises the following steps: fusing meteorological, hydrological and pile deformation multi-source data through a dynamic weight distribution mechanism, and generating a space-time associated dynamic load spectrum by adopting wavelet packet transformation and entropy feature extraction; a collaborative analysis architecture of a finite element simulation and machine learning agent model is constructed, an anchoring depth mapping relation and a real-time design parameter adjustment instruction are output in parallel, and macroscopic fluid parameters and microscopic material degradation characteristics are associated through a data cascade interaction correction mechanism; full-life-cycle data version management is achieved through the block chain technology, and finite element model re-calibration and protection strategy dynamic updating are triggered. The dynamic load response analysis precision and long-term stability of the pile foundation are improved, and the deformation coordination requirement of the flexible support in the complex water area environment is met.

The invention discloses a metal surface quality detection method and system, and relates to the technical field of metal surface quality detection. The method is used for solving the problems of low microdefect detection precision, weak technological parameter relevance and closed-loop control deficiency of the high-reflection surface. The metal surface is irradiated through multi-angle coherent light field serialization, the phase offset of interference fringes is analyzed to generate three-dimensional shape data, and reflection noise interference is restrained. Defect depth gradient is extracted based on dynamic segmentation of process parameter constraint, deposition temperature and pressure deviation are quantified through deconvolution calculation, and process deviation feature distribution is constructed. Finite element simulation is utilized to generate a process-morphology mapping atlas library, cross-domain invariance features are extracted through depth constraint manifold alignment and comparative learning, and a causal correlation model of defect types and process parameters is established. And dynamically adjusting process parameters according to the weight gradient, and reflowing data to update the manifold rule. And high-precision three-dimensional defect detection, process deviation traceability and adaptive parameter optimization are realized.

The present invention relates to the technical field of electrical equipment monitoring, and in particular to an electrical equipment state monitoring and dynamic test evaluation system, comprising a data acquisition module, a data processing module, a feature extraction module, a dynamic test evaluation module and a state evaluation and prediction module; wherein: the data acquisition module is used for real-time acquisition of raw data during the operation of the electrical equipment; the data processing module is used for processing the raw data collected by the data acquisition module to generate a standardized data set; the feature extraction module is used for extracting relevant feature parameters reflecting fatigue damage accumulation from the raw data; the dynamic test evaluation module is used for simulating the fatigue damage evolution process of the electrical equipment under complex working conditions; the present invention, by real-time monitoring of fatigue damage accumulation of the electrical equipment, combines dynamic test evaluation with finite element simulation technology, accurately predicts the remaining life of the equipment and the time of occurrence of a fault, and improves the accuracy and early warning capability of the equipment health state evaluation.

The invention relates to the technical field of wind power generation, in particular to a long flexible blade monitoring method and system based on multi-source data fusion, which adopts a multi-source data fusion technology, collects optical fiber strain, vibration, environment and image data by arranging sensor nodes on a fan blade, and generates comprehensive feature data through preprocessing; and extracting potential feature vectors by a multi-modal auto-encoder, and mapping the potential feature vectors into predicted stress data by using a physical information neural network in combination with offline finite element simulation data and physical constraint conditions. Then, a control decision is generated through the multi-modal deep fusion network and hierarchical reinforcement learning, the blade state is adjusted in real time, and the model is optimized through a closed-loop feedback mechanism; according to the invention, precise monitoring and active regulation and control of special working conditions such as blade pollution and icing are realized.

The invention provides a multi-source heterogeneous data fusion side slope digital twin modeling method, which comprises the following steps of: acquiring side slope multi-dimensional monitoring data by arranging a GNSS (Global Navigation Satellite System) sensor, a multi-point displacement meter, a distributed optical fiber strain sensor, an accelerometer, an osmometer, a monocular camera and satellite remote sensing image equipment; the collected data is converted into a unified format through time alignment, space registration and standardization processing and serves as modeling input; the method comprises the following steps: constructing an initial digital twinborn model reflecting the real form and physical characteristics of a slope by utilizing a three-dimensional modeling and finite element simulation technology; in combination with real-time sensing data, model evolution is dynamically driven based on a space-time fusion algorithm, boundary conditions and material parameters are automatically corrected through actual measurement deviation feedback, and continuous twin iteration updating of the model is achieved; and finally, extracting a landslide risk index to realize real-time early warning of the side slope. According to the invention, multi-source sensing and digital twinborn fusion is realized, and the accuracy, real-time performance and intelligent level of slope monitoring are improved.

The invention provides a crane balance beam crack defect detection method and system, and relates to the technical field of defect detection.The crane balance beam crack defect detection method comprises the steps that a plurality of ultrasonic guided wave sensor arrays are arranged on the surface of a crane balance beam to be detected, ultrasonic guided wave signals in the balance beam are collected, and ultrasonic guided wave time-frequency domain feature vectors of the balance beam are constructed; constructing a three-dimensional finite element simulation model of the crane balance beam to obtain multiple groups of balance beam crack defect expansion strain field data, and constructing a crack defect deformation ultrasonic-strain field fusion feature vector; training a crack defect deformation detection intelligent discrimination model by using the crack defect deformation ultrasonic-strain field fusion feature vector, obtaining a time-frequency domain feature vector and a strain distribution feature vector of the crane balance beam to be detected, and inputting the time-frequency domain feature vector and the strain distribution feature vector into the trained crack defect deformation detection intelligent discrimination model for intelligent discrimination screening. And outputting a crack defect detection result of the balance beam to be detected, wherein the crack defect detection result comprises the type, size, form and specific position of the crack defect.

The invention provides a degradable plastic production method which comprises the following steps: acquiring an optimal raw material proportioning scheme, and controlling an intelligent batching system to perform automatic batching; temperature and humidity parameters of raw material storage and conveying links are obtained, and raw material pretreatment process parameters are dynamically adjusted in combination with time sequence data analysis; performing quality detection on the preprocessed raw materials, identifying defects and impurities of the raw materials by adopting machine vision and a deep learning algorithm, and removing unqualified raw materials; various raw materials are accurately weighed through an industrial robot and mixed according to the optimized formula proportion; a thermal infrared imager is adopted to monitor temperature field distribution of a plastic extrusion forming mold in real time, and finite element simulation analysis is combined to optimize mold structure design and a heating and refrigerating system; the extrusion molding process is monitored on line, material component changes are analyzed through a chemometrics model, and if degradation products exceed the standard, extrusion process parameters are adjusted or a mold is replaced.

The invention discloses a valve performance simulation and optimization method and system based on mixed deep learning, and the method comprises the steps: S1, carrying out the finite element simulation analysis of a valve, and solving through the thermosetting coupling of a multi-physics field, stress, deformation and temperature distribution data of the valve under different working conditions and maximum thermal stress and maximum thermal deformation displacement of key parts of the valve are obtained; s2, after data processing, taking stress, deformation and temperature distribution data of the valve under different working conditions as input parameters, taking maximum thermal stress and maximum thermal deformation displacement as output parameters, training a neural network model, and establishing a thermal-structural performance prediction model; s3, on the basis of a prediction result, a reference point-based non-dominated genetic algorithm is adopted, a reference point generation and self-adaptive agent model is combined, and multi-objective optimization is carried out to output an optimal parameter combination so as to adjust valve design; according to the invention, deep learning and multi-objective optimization are carried out on the finite element simulation result by using the neural network, and the valve performance prediction precision and optimization efficiency are improved.

The invention discloses a numerical control machining path control system based on artificial intelligence, particularly relates to the field of numerical control machining, is used for solving the problems of continuity and stability of a curvature mutation area in cutter path planning, and accurately captures global and local geometric characteristics of a curved surface through a curvature constraint feature matrix and a curvature adaptive convolutional network. A machining track meeting the differential geometric continuity is generated, and the problem of path breakage of a curvature sudden change area is effectively avoided; meanwhile, energy scale criteria and curvature manifold constraints are introduced, the machining track is dynamically repaired, geometric repair and physical stability are balanced, cutting force sudden change and stress concentration are reduced, and therefore the machining reliability is enhanced; in addition, through finite element simulation of the digital twin platform and synchronous updating of servo system parameters, dynamic closed-loop matching of a control instruction and a machining state is achieved, and the control efficiency and the surface quality are further optimized. And therefore, high-precision, high-stability and high-efficiency collaborative optimization is realized in complex curved surface processing.

The invention discloses an intelligent fault diagnosis method fusing state monitoring and a multi-modal large model, and the method specifically comprises the steps: synchronously collecting time sequence data and a space image through a heterogeneous sensor group and monitoring equipment disposed in power grid equipment, and forming original data; based on the original data, a physical constraint feature vector is generated in combination with an equipment thermodynamic equation and a material deformation rule; performing health index prediction through the lightweight LSTM network based on the physical constraint feature vector; when detecting that the health indexes continuously decrease, clustering an HI time sequence curve by adopting a Gaussian mixture model, judging a degradation stage according to a clustering center distance, and obtaining a stage recognition result; and based on finite element simulation parameters, introducing a reinforcement learning model, optimizing the simulation parameters by taking maintenance cost minimization as a target, and outputting a predictive maintenance work order. According to the invention, intelligent fault diagnosis and accurate maintenance of the power grid equipment are realized, the fault processing efficiency and accuracy are improved, and the power failure loss is reduced.

The invention relates to a structural parameter construction method for reducing vibration of a transformer. The method comprises the following steps: acquiring vibration characteristics and working condition data of the transformer; constructing a genetic algorithm model based on the objective function; candidate solution vibration performance verification based on finite element simulation; constructing a hybrid optimization strategy based on a genetic algorithm and finite element simulation; verifying and optimizing the scheme under a multi-dimensional working condition; outputting a vibration calculation result and evaluating a scheme. According to the structural parameter construction method for reducing the vibration of the transformer, the preliminary schemes are screened by applying a fast convergence genetic algorithm, and the candidate schemes are subjected to high-precision verification in combination with finite element simulation, so that the defects of a traditional vibration calculation method in the aspects of efficiency and accuracy are overcome; and the design change can be quickly responded, and the vibration performance is optimized, so that the high-standard requirements of modern power equipment on the aspects of safety and reliability are met, and powerful technical support is provided for the design and improvement of the transformer.

The invention discloses a comprehensive performance prediction and structural parameter optimization method for a hemispherical resonator, and belongs to the technical field of aerospace inertia. According to the method, a high-precision finite element simulation model of the ideal hemispherical harmonic oscillator is established based on a multi-region grid uniform division method; aiming at the condition that each structure parameter corresponds to different structure sizes, calculating through a finite element model of a control variable to obtain a data set of different performance parameters of the hemispherical resonator; based on a BP neural network algorithm optimized by a particle swarm optimization algorithm, after the data set is divided into a training set and a test set, a comprehensive performance parameter prediction model of the hemispherical harmonic oscillator is established; and taking the PSO-BP neural network model as the input of a second-generation non-dominated sorting genetic algorithm, and performing multi-objective optimization on the structural parameters of the hemispherical harmonic oscillator by taking higher thermoelastic damping and larger minimum frequency difference between the interference modal and the PSO-BP neural network model as optimization objectives. The use performance of the hemispherical resonator is improved, and the performance requirement of the aerospace technology field on the high precision of the hemispherical resonator gyroscope is met.

The invention relates to the technical field of computer science, in particular to a stamping prediction method based on a multi-machine learning model and an automatic compensation device.The stamping prediction method comprises the steps that firstly, a sheet microstructure and material characteristics are obtained through a transmission electron microscope and an atomic probe tomography technology, and then finite element simulation sampling is conducted; a data set is expanded by using an adaptive algorithm, multiple models are constructed and trained to obtain a final springback prediction model, an automatic compensation device is embedded to realize automatic compensation, and the automatic compensation device covers visual parameter input, embedded springback prediction, springback compensation calculation and an automatic control module. Parameters can be visually input, springback can be accurately predicted, a compensation value can be calculated, and the process can be adjusted. The method aims at solving the problems that in the high-strength plate stamping process, due to springback, the size and shape of a part deviate from the design requirement, and a traditional prediction and compensation technology is insufficient in precision and efficiency.

The invention relates to the field of durability evaluation and life prediction of reinforced concrete structures, in particular to a reinforced concrete life prediction system and method based on material degradation simulation, and the system comprises an erosion leading edge tracking module which employs a three-dimensional convolutional neural network fused with topology invariance to extract chloride ion distribution image features, generating steel bar corrosion front three-dimensional coordinates and depth information; the transfer learning parameter inversion module is used for inputting the steel bar corrosion front three-dimensional coordinates into a finite element simulation platform, executing parameter inversion calculation and generating a corrosion rate evolution curve; the corrosion rate prediction module is used for generating a corrosion rate prediction curve by using a long-short-term memory network; and the online correction module is used for collecting temperature and humidity information in the concrete structure, calculating the influence weight of environmental factors on the corrosion rate, correcting a corrosion rate prediction curve, updating long-term and short-term memory network parameters, identifying and tracking the steel bar corrosion leading edge in a high-precision manner, and accurately capturing a complex three-dimensional corrosion form.

The invention belongs to the technical field of thermal circuit model construction, and particularly relates to a high-voltage power cable intermediate connection thermal circuit fault modeling analysis method and device, and the method comprises the steps: building a high-voltage power cable intermediate connection thermal circuit fault circuit model through analyzing a cable intermediate connection temperature inversion principle; the method comprises the following steps: establishing a geometric model for multi-physics field analysis of the intermediate connection of the high-voltage power cable by utilizing Comsol finite element simulation software, setting material parameters of each component, and setting field domain parameters; an electromagnetic field module is added, boundary conditions of electromagnetic field analysis are set, and a cable intermediate connection electromagnetic field simulation model is obtained; adding a solid heat transfer module to obtain a solid temperature field simulation model; obtaining an electromagnetic-thermal coupling model, and solving to obtain the temperature, current and loss of the cable middle connection wire core and the outer surface in different insulation states. According to the method, the cable intermediate connection fault problem can be found and predicted, and the reliability and the safety of the power cable are improved.

The invention discloses an intelligent monitoring management system and method for a wire harness production line, and relates to the technical field of wire harness manufacturing, and the method comprises the steps: extracting data of crimping force and mold temperature from historical wire harness production data, coding the data into a real number coding gene chain, generating an initial gene pool in combination with material attributes, and constructing a digital twin model; the method comprises the steps of simulating stress field distribution and a heat conduction effect in a wire harness crimping process through finite element simulation, obtaining a twinning predicted value, pre-verifying process parameters in an initial gene bank based on a digital twinning model, screening process parameter combinations with deformation errors smaller than an error threshold value, and issuing the process parameter combinations to a crimping machine through a production line control center. According to the method, data of real-time wire harness deformation quantity is obtained, the data of the real-time wire harness deformation quantity is compared with a twinborn predicted value frame by frame, a deformation error rate is generated, and an abnormal traceability report is generated based on the deformation error rate, pre-verification is performed by constructing an initial gene pool and combining a digital twinborn model, so that optimization of process parameters is more accurate and effective.

The invention relates to the technical field of track structure health monitoring, in particular to a track crack recognition and fatigue life prediction method and system based on deep learning and finite elements, and the method comprises the steps: collecting and preprocessing a track surface crack image, and obtaining crack image data; a deep neural network model is trained, and a corresponding track crack recognition algorithm based on deep learning is determined; identifying and extracting positions and geometric dimensions of the cracks; based on the geometrical characteristics and the material attributes of the track, establishing a corresponding track finite element model, and inputting the position and the geometric size of the crack into the track finite element model to generate and obtain a track model containing crack damage; based on wheel-rail rolling contact fatigue finite element simulation, simulating the mechanical response of a track structure, determining the fatigue life of the track in combination with the stress-strain distribution of the track, and predicting the development trends of cracks under different operation conditions; automatic and efficient identification of track cracks is realized, and the accuracy of fatigue life evaluation is improved.

The invention provides a test risk digital twinning early warning method based on multi-domain cooperative monitoring, and belongs to the technical field of virtual-real fusion test and digital twinning, and the method comprises the steps: firstly, building a fine finite element simulation model which comprises a digital tool system, a digital sensor and a test piece and considers nonlinearity; secondly, performing nonlinear finite element simulation analysis, and constructing a multi-level mechanical response field inversion reduced-order model; thirdly, completing the construction of a complete sensor data set through a data filling algorithm, and carrying out the failure judgment of the first hierarchical structure based on the complete sensor data set; and finally, carrying out future loading level sensor data prediction and completing failure judgment of a second hierarchical structure. Carrying out full-field mechanical response inversion and online real-time correction; and performing response inversion of the region of interest to realize failure judgment of the third hierarchical structure. According to the invention, real-time dynamic monitoring and early warning of the structure test risk can be realized, the real-time performance, the robustness and the accuracy are high, and a powerful guarantee is provided for the safety and the reliability of the structure test.

The invention relates to the technical field of finite element simulation modeling, in particular to a model construction method, device and equipment for simulating an air effect in a honeycomb aluminum barrier. The method comprises the following steps: building a target honeycomb block simulation model containing a single-degree-of-freedom discrete beam unit; performing a quasi-static working condition test, and performing benchmarking to construct a honeycomb block static extrusion target simulation model based on a result of the quasi-static working condition test and the target honeycomb block simulation model; a dynamic working condition test is carried out, and a honeycomb block finite element model coupled with the air effect is constructed through benchmarking based on the result of the dynamic working condition test and the honeycomb block static extrusion target simulation model; and on the basis of the honeycomb block finite element model of the coupling air effect, according to a preset skin grid and a preset connection relation, a honeycomb aluminum barrier overall model is generated. Therefore, the problems that in the prior art, the simulation result of automobile collision is inaccurate, and automobile body deformation does not conform to reality are solved, the automobile collision simulation accuracy is improved, and the calculation accuracy and efficiency of the obstacle avoidance working condition are optimized.

The invention discloses a vehicle surrounding structure fault prediction maintenance method and system based on machine learning, and relates to the technical field of vehicle intelligent monitoring and prediction maintenance. Through fusion of vibration, strain and environment corrosion data and a finite element simulation stress map, an environment-load collaborative damage effect is quantified through a physical degradation model, and a multi-modal feature vector is generated. Constructing a dynamic graph topology network, adjusting edge weights in real time, and synchronously capturing spatio-temporal mechanics characteristics by using spatio-temporal graph convolution; and further identifying key risk nodes through a graph attention mechanism, simulating a damage propagation path in combination with a corrosion attenuation coefficient and a graph diffusion model, and generating a probabilistic fault thermodynamic diagram. The fault prediction precision of the vehicle surrounding structure is improved, an adversarial generative network is constructed to optimize the sample weight, and a quantile maintenance list is output in combination with a physical constraint loss function. Fault prediction and maintenance optimization of the vehicle surrounding structure can be effectively carried out, the service life of the structure is prolonged, and the maintenance cost is reduced.

The invention relates to the technical field of semiconductor device testing, in particular to a SiC MOSFET power cycle testing method which comprises the following steps: S1, building a composite environment testing platform, configuring dynamic testing parameters, automatically calculating a physical boundary and collecting sensor data in real time; s2, establishing a finite element simulation model based on the physical boundary and sensor data, and outputting optimized dynamic test parameters and a simulated stress distribution diagram; s3, synchronously applying composite stress according to the dynamic test parameters and the stress distribution diagram, and collecting multi-dimensional test data in real time; when the system is used, through dynamic boundary calculation and real-time data acquisition, the intelligent degree and reliability of the test are improved, the test period is shortened, the failure prediction accuracy is improved, the system is suitable for reliability evaluation of SiC MOSFET devices in the fields of new energy, aerospace and the like, a large number of physical tests are avoided through virtual simulation, and the reliability of the SiC MOSFET devices is improved. And reduction of device loss and resource waste is facilitated.

The invention discloses a probe card simulation method and system based on counter-acting force analysis, which are used in the field of wafer simulation test, and the probe card simulation method comprises the following steps: integrating multiple physical field working conditions to construct a probe card geometric model, and importing the probe card geometric model into finite element simulation analysis software; carrying out grid division on the geometric model of the probe card by utilizing the hybrid voxel tree model, adjusting the grid density according to the distribution requirement of the multi-physical field, and setting a simulation boundary condition by utilizing a preset boundary condition template according to the actual simulation requirement; starting a simulation calculation process based on the adjusted grid density and simulated boundary conditions; and providing a visual interface of physical field distribution and a structural stress state in the simulation calculation process, and performing iterative optimization on the performance of the probe card in the simulation process according to a reactive force distribution result. According to the method, the grid density is automatically adjusted to adapt to changes of a physical field, and it is ensured that higher simulation precision is obtained in a key area.

The invention provides a macroscopic finite element simulation analysis method and device for a sealing element considering plastic deformation, and belongs to the field of sealing element design. The method comprises the following steps: acquiring an engineering stress-strain curve of a plastic material in a compression state; converting the engineering stress-strain curve into a real stress-strain curve; determining a yield limit, and taking a strain point corresponding to the yield limit as a demarcation point of elasticity and plastic deformation; an elastic section of a real stress-strain curve is extracted, the elastic modulus is calculated, and the Poisson's ratio is obtained through axial and transverse strain measurement in a uniaxial compression test; a true stress-strain curve plastic section is extracted, and a multi-linear isotropic hardening model is established; constructing a complete elastic-plastic constitutive model covering the elastic deformation area and the plastic deformation area; the stress distribution, the strain response and the contact performance of the plastic sealing element in a compression deformation state are simulated. According to the method and the device provided by the invention, the problem that the result does not conform to the reality due to the fact that only elastic modulus and Poisson's ratio are used in existing sealing element simulation can be solved.

The invention belongs to the crossing field of road engineering technology, artificial intelligence and engineering mechanics, and particularly relates to a road structure design method based on a large model and reinforcement learning. A technical closed loop of'natural language input-parameter automatic mapping-specification standard value acquisition-finite element verification-reinforcement learning optimization 'is constructed: by constructing a load parameter mapping table and a material semantic encoder, the system can automatically convert natural language input into engineering parameters such as load, material, layer thickness and the like, and the problem of adaptability to non-standard working conditions is solved. And a deviation characteristic space is constructed by further combining a mechanical theory solution and finite element simulation, and the reinforcement learning agent is driven to quickly optimize under the condition of meeting theoretical constraints. Compared with a traditional trial calculation method and an existing intelligent optimization scheme, the method has the advantages that the number of design iterations and the material cost are greatly reduced, the safety and compliance of an output scheme are improved, and intelligent spanning from experience driving to theory guiding is achieved.

The invention belongs to the technical field of connectors and discloses a design method for a low-loss cable connector without resonance points, comprising: designing a spiral gradient groove structure on the surface of an inner conductor based on the impedance continuity principle, establishing a composite gradient impedance theoretical model of the connector, constructing a dielectric constant gradient distribution model of a double insulating layer, and setting a transition function between an inner layer and an outer layer; solving the S parameters and electric field distribution of the connector through electromagnetic-thermal coupling finite element simulation, optimizing the spiral angle θ and the gradient index n, establishing a quantitative model of the surface roughness of the conductor and high-frequency loss, and determining a threshold range of the surface roughness through calculation of the quantitative model; performing global optimization of structural parameters based on a multi-objective genetic algorithm, outputting a theoretical design parameter set and a report collection of performance verification, eliminating the resonance point problem of traditional connectors, and providing excellent low-loss performance in the full frequency band, which is particularly suitable for high-frequency and high-power transmission environments.

The invention discloses a deterministic cutting compensation processing method for an infrared thin-wall optical element. The method comprises the following steps: S1, acquiring an initial surface shape of a workpiece; the method comprises the following steps: measuring an initial surface shape of a thin-wall optical element to be machined through an ultra-precision machine tool in-situ measurement technology to obtain a surface shape outline rho (x, y), and calculating a material removal amount deltaz (x, y) at each coordinate position according to a designed surface shape outline z (x, y), deltaz (x, y) = rho (x, y)-z (x, y); s2, elastic deformation prediction of clamping stress; based on a finite element simulation model, three-dimensional space numerical distribution simulation is conducted on clamping force distribution in the machining process, and element elastic deformation epsilon (x, y) caused by clamping stress is predicted; integrating the elastic deformation amount with the initial material removal amount to obtain a new material removal amount z '(x, y); s3, deformation prediction of the machining residual stress element; s4, generating a non-uniform material removal compensation track; and S5, non-uniform cutting compensation machining based on slow cutter servo is carried out.

The invention belongs to the technical field of finite element simulation optimization, and provides a hot upsetting process multi-target collaborative optimization method and system based on finite element simulation, and the method comprises the steps: firstly constructing a hot upsetting process multi-field coupling finite element model, and then deploying a sensor network in hot upsetting equipment to collect actual process data. Actual data and simulation data are matched through a space-time registration algorithm, then a parameter optimization model is constructed based on a dual-channel depth deterministic strategy gradient algorithm, and a technological parameter solution set is obtained through calculation; and finally, a multi-objective optimization function is defined according to a preset optimization index, and optimal hot upsetting process parameters are screened out in combination with an entropy weight method and a reference point-based non-dominated genetic algorithm. According to the method, high-precision simulation, real-time monitoring and multi-target collaborative optimization of the hot upsetting process are achieved, and the production efficiency and the product quality of the hot upsetting process are remarkably improved.

The invention discloses a digital twin system architecture of a vertical shaft and a structural performance monitoring method. The method comprises the following steps: constructing a five-dimensional digital twin system framework suitable for a vertical shaft based on a shaft operation mechanism and performance monitoring requirements; establishing a shaft digital twinborn model with dynamic characteristics; a finite element proxy model is constructed through a virtual-real mapping technology in combination with a grid dimensionality reduction finite element analysis method, and rapid generation of the digital twinborn body is realized. According to the system, a three-dimensional operation platform is constructed based on a Unity 3D virtual engine, and efficient mapping and bidirectional interaction between twin and finite element simulation data are realized by adopting a radial basis function (RBF) proxy model. And real-time acquisition and online prediction are carried out on structural performance parameters in the shaft operation process. And dynamically updating the twinborn model according to a prediction result, and constructing a high-precision and light-weight digital twinborn evolution model, thereby realizing real-time observation of the stress change of the shaft and intelligent monitoring of the structural performance. The method can be widely applied to the fields of shaft safety assessment, maintenance decision making, intelligent mine construction and the like.

The invention provides a preparation method of an isotropic Ti2AlNb / TiAl-based interpenetrating composite material, and belongs to the technical field of intermetallic compound-based composite materials. The method comprises the following steps: firstly, designing a Ti2AlNb reinforcement framework of various TPMS configurations by utilizing implicit function modeling; then, carrying out anisotropy research on the TPMS configuration by utilizing finite element simulation; secondly, a Ti2AlNb reinforcement framework of a TPMS configuration is prepared through a selective laser melting (SLM) technology; and finally, the TPMS configuration Ti2AlNb / TiAl-based interpenetrating composite material is prepared through vacuum hot pressing sintering of HPS. Therefore, strong anisotropy of a traditional fiber reinforced composite material in mechanical property is avoided, good matching of strength, plasticity and toughness of the composite material is achieved, and a new thought and a new solution are provided for breaking through the application bottleneck of TiAl in spaceflight power system hot end components.