46 results about "Inverse analysis" patented technology

The invention relates to the technical field of layered surrounding rock inversion analysis, and discloses a layered surrounding rock three-dimensional crustal stress field inversion intelligent analysis system and method, and the system comprises a dimensional geological value module, an intelligent inversion analysis module and an inversion result verification module. The method comprises the steps of collecting geological data in target layered surrounding rock; carrying out normalization processing on the geological data, and carrying out sensitivity analysis; constructing a three-dimensional geologic model, and performing numerical simulation; a crustal stress field inversion intelligent analysis model is generated based on the three-dimensional geologic model; training the crustal stress field inversion intelligent analysis model by using the training sample; inputting the real-time geological data into the crustal stress field inversion intelligent analysis model to obtain a crustal stress inversion analysis result; carrying out visual output on the ground stress analysis result; and adjusting the crustal stress field inversion intelligent analysis model according to the actually measured data. Scientific ground stress field analysis basis can be provided for complex projects such as tunnel engineering, underground engineering and hydropower stations.

The invention provides a tunnel deformation parameter inversion method and device based on distributed optical fibers, and relates to the technical field of tunnel deformation parameter inversion, and the method specifically comprises the steps: selecting a monitoring point in a tunnel, arranging an optical fiber sensor, and obtaining a Brillouin scattering signal generated by the optical fiber sensor under the stress effect of the corresponding monitoring point; extracting a Brillouin frequency shift corresponding to the monitoring point, and determining an environmental effect frequency shift correction value by using the temperature change data, the humidity change data and the service time of the optical fiber sensor; determining the structural strain of the monitoring point according to the Brillouin frequency shift and the environmental effect frequency shift correction value, generating a three-dimensional strain field cloud picture, performing spatial registration on the three-dimensional strain field cloud picture and the geometric topology of the model, and performing three-dimensional grid division; the structure strain of the monitoring point is mapped to the grid node at the corresponding position, the structure strain of other grid nodes is determined based on the space distance attenuation law, inversion of the whole tunnel deformation parameters is completed, and the tunnel deformation monitoring precision and efficiency are improved.

The invention provides a landslide prediction method and system based on big data analysis, and relates to the technical field of big data analysis, and the method comprises the following steps: obtaining multi-source geological data of a target region, constructing a three-dimensional geological model, and dividing slope units; calculating an initial safety coefficient of each slope unit by adopting a limit equilibrium method and Monte Carlo simulation; acquiring real-time monitoring data, establishing an inverse analysis optimization model, and inverting and calibrating physical and mechanical parameters; updating calibration parameters to the model, coupling rainfall infiltration and underground water seepage simulation, dynamically updating a pore water pressure field, and calculating a real-time dynamic safety coefficient; and according to a comparison result of the dynamic safety coefficient and a preset threshold value, determining the stable state of the slope and sending out corresponding early warning. According to the method, through multi-source data fusion, parameter dynamic inversion calibration and real-time hydrological and mechanical coupling simulation, accurate and dynamic evaluation and graded early warning of slope stability are realized, and the accuracy and timeliness of landslide prediction are remarkably improved.

The invention relates to an inversion method and system for sedimentation parameters of a working face of a well mine. For a trend subsidence prediction model and a tendency subsidence prediction model, trend model parameter inversion and tendency model parameter inversion are respectively implemented by using a deep neural network, and the deep neural network used for trend model parameter inversion is mainly composed of a full connection layer and an activation function Leaky Relu. The deep neural network for tendency model parameter inversion is mainly composed of a pruned and optimized full connection layer and an activation function SILU, and a loss function is a mean square error between a predicted subsidence value and an actual subsidence monitoring result. According to the method, the parameters of the probability integral model can be learned and inverted from the monitoring data more accurately, so that a more efficient and robust technical means is provided for predicting the ground surface settlement of the mining area, the parameter operation speed is effectively increased, and the parameter error is reduced.

The invention discloses a flood discharge gate structure dynamic load time domain rapid identification and dynamic response field inversion method comprising the following steps: 1) carrying out a vibration test of a flood discharge gate structure, and obtaining a multi-source vibration response signal of the flood discharge gate structure; 2) constructing a unit impulse response matrix H and a load shape function matrix N; 3) establishing an inverse analysis model X = HNA for dynamic load time domain identification of the flood discharge gate structure; 4) inversely solving the load shape function coefficient matrix A to obtain a dynamic identification load of the flood discharge gate structure; and 5) inputting the identification load as an external load of the sluice structure to obtain an overall dynamic response field of the sluice structure.The method is based on the multi-source actual measurement vibration response of the sluice structure, the improved dynamic load time domain identification method based on the shape function is adopted, the time domain load of the sluice structure can be rapidly and effectively identified, and the identification accuracy is high.

The invention provides a forwarding method and device based on a geographic relative position, equipment and a medium, and the method comprises the steps: carrying out the coding according to the geographic space coordinates of producers through employing a Geohash algorithm, and distributing a unique Geohash code for each producer; distributing a Geohash code naming Dpkt to the producer based on a Geohash algorithm, and obtaining a data name of the Dpkt of the producer; performing inverse analysis on the Ipkt data name through the forwarding node to obtain a geographic space coordinate, and determining a geographic relative orientation of the forwarding node and the forwarding target according to the own coordinate of the forwarding node and the geographic space coordinate; and sending the Ipkt to the forwarding interface of the corresponding geographical orientation through the forwarding node. The method has the beneficial effects that the storage overhead of the forwarding plane and the communication overhead between the nodes are reduced, and the reliability of the network is improved.

The invention provides a blasting simulation method and device for crystal intruding rock, and the method comprises the steps: building an initial rock crystal sample uniaxial compression model according to the mesoscopic physical parameters of target crystal intruding rock; generating a cohesive force unit for a contact interface between crystal grains in the uniaxial compression model to obtain a uniaxial compression model of the target rock crystal sample; performing a uniaxial compression simulation test on the uniaxial compression model of the target rock crystal sample to obtain test simulation data, correcting parameters through a back analysis method to obtain target material parameters of a target crystal, and constructing a rock crystal medium blasting construction FDEM model; and according to the rock crystal medium blasting construction FDEM model and the blasting parameters, blasting simulation is carried out on the target crystal intruding rock. Therefore, according to the scheme, by designing the finite-discrete coupling blasting simulation method, the cost can be reduced, the time consumption can be reduced, and the dynamic response rule and the damage mechanism of the rock mass in the blasting process can be quantitatively represented.

The invention belongs to the technical field of water conservancy and hydropower engineering, and particularly relates to a grotto side wall mechanical parameter displacement back analysis method based on a fungus growth optimization algorithm, which comprises the following steps of: 1, establishing an underground powerhouse FLAC3D numerical model by adopting an elastic-plastic constitutive model conforming to a Hook-Brown failure criterion; 2, converting a parameter back analysis problem into an optimization problem, and determining optimization variables of the mechanical parameters of the side wall of the numerical model; step 3, establishing a displacement error minimum optimization objective function; and 4, solving the target function by adopting an FGO optimization algorithm, and searching global optimal side wall mechanical parameters. According to the method, the rock mass engineering design problem that on-site large-size rock mass mechanical parameter values cannot be accurately obtained based on small-size rock samples due to the remarkable rock mass scale effect is effectively solved.

The invention discloses an underground water reactive solute transport inversion method, device and system and a storage medium, and the method comprises the steps: building a potential nonlinear mapping relation between a low-fidelity substitution model and a high-fidelity numerical model through a series neural network based on a multi-fidelity substitution model adaptive updating strategy through a deep neural network; in an iterative inversion process, a training sample data set is adaptively updated, and the prediction precision of the substitution model in a real parameter posterior distribution region is gradually improved, so that a final inversion identification result of model parameters is improved. By adopting the technical scheme of the invention, an accurate model parameter inversion recognition result can be given under the condition of limited forward model implementation times, and the calculation efficiency and the prediction precision are remarkably improved.

The invention discloses a bridge vehicle load inversion method and system based on dynamic deflection, and the method comprises the following steps: constructing a bridge information database which stores bridge structure type information, vehicle actuation deflection variation amplitudes, vehicle load data, and probability arrays of vehicle load data corresponding to different vehicle actuation deflection variation amplitudes; reading to-be-inverted dynamic deflection monitoring data, and calculating the change amplitude of the vehicle actuating deflection of the to-be-inverted dynamic deflection monitoring data; reading corresponding vehicle load data and a probability array according to the current bridge type information and the vehicle actuation deflection variation amplitude of the dynamic deflection monitoring data to be inverted; and taking the probability of the vehicle load data as a weight, determining an interval in which the vehicle load is located by adopting weighted sampling, and determining the vehicle load of the dynamic deflection monitoring data to be inversed in the interval by adopting simple random sampling. According to the method, the importance evaluation value of the influence of the vehicle on the crack is further constructed based on the vehicle actuation deflection change amplitude, the crack development is tracked and positioned, and the vehicle load effect evaluation is realized.

The invention provides a concrete structure construction period temperature deformation cracking risk prediction method comprising the following steps: S1, temperature monitoring: after concrete structure pouring is completed, continuously monitoring a concrete internal and surface temperature development curve; s2, inverting thermal parameters, namely inverting an equivalent adiabatic temperature rise curve and an equivalent thermal diffusivity of concrete under a field condition and a convective heat transfer coefficient of the concrete under a template in-place condition by combining a monitoring temperature, an environment temperature and a heat preservation condition and utilizing a heat conduction equation inverse analysis method; s3, prediction in the form removal period and the later period: inputting the thermal parameters obtained by inversion into finite element software, performing temperature field prediction, switching a boundary condition to be a heat exchange coefficient after form removal, and simulating subsequent temperature evolution; s4, risk index calculation and grading: calculating a risk index, and quantifying or grading the cracking risk according to a set threshold value; s5, performing construction decision linkage; according to the method, the thermal parameters of the concrete can be quickly inverted by utilizing early field measured temperature data.

The invention discloses an extremely soft phyllite tunnel surrounding rock parameter inversion method and system, and relates to the technical field of tunnel engineering. Comprising the following steps: acquiring basic mechanical parameters, partial pressure parameters and damage parameters of a rock mass; determining to-be-inverted parameters of the rock mass and setting a value range, and performing sensitivity analysis on the to-be-inverted parameters; carrying out a mixed horizontal orthogonal experiment on the to-be-inverted parameters based on a sensitivity analysis result, and carrying out numerical simulation on the rock mass; constructing a prediction model by utilizing a support vector machine (SVM), taking a numerical simulation result as input, and training the model by adopting a random division cross validation method; and predicting the optimal solution of the to-be-inverted parameters of the rock mass by using the trained prediction model. Based on sensitivity analysis of a single to-be-inverted parameter of the HJC model, parameters which greatly influence response variables are identified, so that the proportion of the key factors in a mixed level orthogonal experiment is increased by focusing on the key factors, and the efficiency and accuracy of model training are greatly improved.

The invention provides a gravity dam anti-seismic capacity analysis method considering an anti-seismic reinforcement reinforcement effect. The gravity dam anti-seismic capacity analysis method comprises the steps that a gravity dam cross-joint reinforcement reinforcement model is constructed; the gravity dam joint-crossing reinforcing steel bar model comprises a dam body concrete structure, a crack structure and reinforcing steel bars penetrating through the crack structure to be reinforced. Determining the optimal value of the physical and mechanical parameters of the dam body concrete structure by using an inverse analysis method and combining an iterative optimization algorithm; the optimal values of the physical and mechanical parameters of the dam body concrete structure serve as initial parameters of the gravity dam cross-joint reinforcing steel bar model; and seismic acceleration is applied to the gravity dam joint-crossing reinforcing steel bar model, the multiple of the seismic acceleration is gradually increased, and anti-seismic simulation analysis is carried out. According to the gravity dam anti-seismic capacity analysis method considering the anti-seismic reinforcement reinforcement effect, the anti-seismic capacity of the gravity dam with cracks after anti-seismic reinforcement reinforcement can be accurately analyzed.

To improve estimation accuracy of an underground structure.SOLUTION: In the underground structure estimation method, micromotion of the soil at observation points P1 to P6 is observed by a micromotion array 10, and at least an S-wave speed Vs1 in a base layer 1 and a depth H to an upper surface 1a of the base layer 1 are calculated by inverse analysis using a relationship between a frequency and a phase speed of a wave propagating through the soil G from the observed micromotion, thereby estimating an underground structure at the observation points P1 to P6. In the subsurface structure estimation method, predetermined observation points among the plurality of observation points P1 to P6 are grouped as group observation points Pg, inverse analysis is performed assuming that the S-wave velocities Vs1 in the base layer 1 at all the grouped group observation points Pg are the same, and the S-wave velocities Vs1 in the base layer 1 and the depth H to the upper surface 1a of the base layer 1 at each of the group observation points Pg are calculated.SELECTED DRAWING: Figure 1

The objective is to provide a system that can identify the parameters necessary for development calculations, even when dealing with photosensitive resin compositions that are scattering materials. [Solution] A parameter search device comprising: an acquisition unit that acquires at least one measured value of information relating to the minimum exposure amount or curing rate at which the film thickness does not decrease by development, and information relating to the maximum exposure amount or curing rate at which the film is substantially removed by development, when a resin layer is exposed with stepwise exposure amounts or cured to a predetermined degree by said exposure and then developed under predetermined development conditions; and a search unit that uses the measured value to search for parameters relating to coefficients or constants of a development speed calculation model by inverse analysis.

The present invention provides a method and product for calibrating the soil erosion parameters of a landslide dam using an inverse analysis method, which relates to the technical field of data processing. In the embodiments of the present invention, the average soil erosion parameters at different depths are characterized by the trend component function in the random field theory, and based on this, the calibration work of the soil erosion parameters of the landslide dam is carried out. According to the erosion parameter records at different depths in several landslide dam cases, a multi-criteria decision-making method is used to determine the best type of trend component function under the existing conditions. In addition, the embodiments of the present invention also use two complementary inverse analysis methods to calibrate the trend component function. One method is a deterministic inverse analysis based on multi-objective optimization to determine the best trend component function; the other method is a probabilistic inverse analysis based on Bayesian theory to quantify the uncertainty of the trend component function. The trend component function determined in the embodiments of the present invention can effectively describe this trend. The soil erosion parameters calibrated by the inverse analysis method can obtain good simulation results.

To provide a coating condition prediction system capable of determining a coating condition for a coater within a short period and reducing a paint loss through determination of an optimal coating condition.SOLUTION: This coating condition prediction system for predicting an optimal coating condition for a coater comprises: coating model construction means; film thickness value prediction means; and coating condition prediction means. The coating model construction means accumulates data relating to coating conditions X1-X9 and workpiece shape data, and constructs a coating model that outputs a prediction value of a film thickness value of a film formed on the surface of a workpiece. The film thickness value prediction means predicts a film thickness value by accumulating the data relating to the coating conditions X1-X9 for the coating model. The coating condition prediction means predicts the optimal coating condition by performing reverse analysis using the coating model upon entry of a target film thickness value and the workpiece shape data.SELECTED DRAWING: Figure 5

The present invention relates to the technical field of machine learning, and more particularly to a method, system and storage medium for inverting the rock mass in-situ stress field based on machine learning. Step S1: Construct a three-dimensional virtual model of the target rock mass and obtain the geological data at each position in the inversion target area; Step S2: Obtain the geological types in the inversion area and obtain the rock mass parameters of the rock mass corresponding to the sampling points; Step S3: Obtain a number of groups of test data through the hydraulic fracturing method and the borehole method respectively, perform preprocessing, and obtain learning data and detection data; Step S4: Create a rock mass stress prediction model, the rock mass stress prediction model includes m sub-models, train the sub-models using the learning data, and verify the sub-models based on the detection data. The present invention solves the problem of inaccurate inversion of the rock mass stress field and improves the inversion accuracy of the rock mass in-situ stress field.

To provide a method for searching for a sol-gel film which is a coating film including metal alkoxide, a computer, and a program.SOLUTION: A method for searching for a sol-gel film including metal alkoxide, executed by a computer, includes the steps of: generating a plurality of prediction models corresponding to a plurality of objective variables using result data relevant to a sol-gel film; and searching for a sol-gel film having a desired physical property balance by reverse analysis using a plurality of prediction models. The result data includes at least type and ratio of the metal alkoxide and synthesis information of the sol-gel film. The objective variables include at least one of the numerical values representing optical property, mechanical property, superficial, and chemical property.SELECTED DRAWING: Figure 4

Compared to cases where weights are not included in the inverse analysis, we obtain an inverse analysis method that can derive parameters with higher accuracy. [Solution] The inverse analysis method by the inverse analysis device 10 is an inverse analysis method that performs inverse analysis using an objective function that obtains the sum of the differences between observed values ​​of predetermined types of physical quantities at multiple locations and calculated values ​​obtained by forward calculation using a mathematical model that approximates the actual field using predetermined parameters corresponding to the observed values, with weights applied to each of the multiple locations, and the parameters and weights are the targets of the inverse analysis.

This invention belongs to the field of 3D image rendering technology, and relates to a method and system for modeling and rendering packaging boxes. The invention generates a basic 3D mesh model by acquiring 2D die-cutting line data of the packaging box, extracts physical parameters of the substrate, binds features to the model, constructs multi-layer material rendering channels for optical interference calculations, and generates a model with anti-counterfeiting visual features. Further, through thermodynamic deformation calculations, a rendering model containing physical indentations is generated. Through interference verification and inverse analysis of 3D spatial features, physical processing control quantities are generated to drive production equipment to achieve automated linkage control of the packaging box. This invention solves the problem of traditional rendering mechanisms lacking accurate representation of physical deformation and complex optical scattering, improves the realism and physical accuracy of the rendered model, breaks down the data barriers from 3D rendering to physical processing, and provides effective support for high-precision packaging box production.

This invention relates to the field of tunnel and underground engineering safety monitoring technology, and discloses a method and system for graded early warning of water-soil coupled disasters in soft strata tunnels based on mechanism inversion. The method includes: using multi-scale coupling technology to parametrically couple a pre-constructed macroscopic continuous medium model and a microscopic constitutive model, and generating a mechanism inversion model based on the parameter coupling results to simulate the water-soil coupled disaster response of the tunnel surrounding rock; inputting pre-processed historical monitoring data into the mechanism inversion model, iteratively adjusting the parameters of the mechanism inversion model through inverse analysis to generate a combination of inversion parameters; and inputting pre-processed real-time monitoring data into the corrected mechanism inversion model. This invention, through local mesh refinement and erosion interface mapping based on level set functions, accurately embeds a microscopic constitutive model capable of describing soil particle migration and pore evolution into high-risk areas of the surrounding rock, achieving coupling of macroscopic and microscopic physical processes at key locations.

The invention discloses a support design reliability back analysis method under a deep roadway surrounding rock plate crack instability mode, and belongs to the technical field of mine underground roadway engineering support stability and reliability design. The method comprises the following steps: constructing a limit state equation containing support design decision parameters in a surrounding rock plate crack instability mode based on a sudden change theory; aiming at a preset reliability measurement standard in the support design, solving and calculating support design decision parameters by using a reliability back analysis method, and comparing the result with a result obtained by a traditional reliability positive analysis method to verify the feasibility and rationality of the reliability back analysis method; and on the basis, starting from different preset reliability measurement standards, supporting design under various working conditions in the surrounding rock plate crack instability mode is further carried out through a reliability back analysis method. According to the method, a calculation result which meets a preset reliability measurement standard requirement and has relatively high precision can be obtained, the number of iterative loop operations is small, and solution analysis is convenient and efficient.

The invention discloses a seabed pipe jacking construction vertical jacking force prediction method based on a correction shear theory, and belongs to the technical field of underground tunnel engineering. The prediction method comprises the steps of analyzing components of jacking force F in vertical jacking method construction, determining a fracture angle alpha ', correcting an expression of the fracture angle alpha' according to actually measured data, calculating geometric parameters of a soil body in a shear failure surface, calculating a head-on resistance Fh value, calculating a pipe wall friction resistance Ff value and calculating the jacking force F value. An expression that the fracture angle changes along with the pushing distance of the jacking pipe is deduced by combining an existing soil body shear failure theory and a measured data inverse analysis method, so that the dynamic change of the soil body form in a shear failure surface and the head-on resistance in the whole construction process of the vertical jacking method can be accurately reflected; different construction conditions are considered in calculation of the frictional resistance of the pipe wall; the self weight of the jacking pipe and the water pressure above the jacking pipe are determined by combining the shear failure theory, and the jacking force of the whole construction process of the vertical jacking method can be predicted more accurately.

The present invention discloses a method and system for inverse analysis of mechanical parameters of roller compacted concrete dams, which relates to the technical field of deformation monitoring of roller compacted concrete dams. It includes: obtaining a data sample set; establishing an MLSSVR model according to the data sample set; obtaining the displacements of each monitoring point of the roller compacted concrete dam by using the data sample set according to the MLSSVR model; calculating the fitness value g(x) of the objective function and taking the minimum value; obtaining the inverse value x of the mechanical parameters that makes the objective function g(x) the minimum value. The inverse analysis method of mechanical parameters of roller compacted concrete dams based on MLSSVR in the present invention shows good results in inverse analysis of mechanical parameters of roller compacted concrete dams; the MLSSVR model can replace the finite element method to reflect the non-linear mapping relationship between mechanical parameters and dam displacements, and can perform reliable inverse analysis on the mechanical parameters of roller compacted concrete dams, improving the accuracy and efficiency of inverse analysis of mechanical parameters of roller compacted concrete dams.

The invention discloses a BIM (Building Information Modeling)-based shield engineering stratum identification and construction parameter optimization method. The method comprises the following steps: establishing a shield construction simulation model for obtaining a shield deformation data analysis process from stratum parameters and construction parameters based on BIM modeling software; a sparrow optimization algorithm is introduced on the basis of a random forest algorithm model, an RF-SSA-based stratum parameter back analysis identification model and an RF-SSA shield construction parameter back analysis model are constructed, and through an optimization method combining the two models, rapid and accurate identification of shield construction stratum parameters is realized, and the method can adapt to a complex and changeable construction environment and is high in practicability. And the dynamic optimization of the shield engineering construction parameters is further realized. The method solves the problem that a traditional method mainly depends on experience and limited geological survey data and is difficult to adapt to complex and changeable construction environments, and consequently high uncertainty and risks exist in the construction process.

This invention relates to the field of tunnel and underground engineering safety monitoring technology, and discloses a method and system for graded early warning of water-soil coupled disasters in soft strata tunnels based on mechanism inversion. The method includes: using multi-scale coupling technology to parametrically couple a pre-constructed macroscopic continuous medium model and a microscopic constitutive model, and generating a mechanism inversion model based on the parameter coupling results to simulate the water-soil coupled disaster response of the tunnel surrounding rock; inputting pre-processed historical monitoring data into the mechanism inversion model, iteratively adjusting the parameters of the mechanism inversion model through inverse analysis to generate a combination of inversion parameters; and inputting pre-processed real-time monitoring data into the corrected mechanism inversion model. This invention, through local mesh refinement and erosion interface mapping based on level set functions, accurately embeds a microscopic constitutive model capable of describing soil particle migration and pore evolution into high-risk areas of the surrounding rock, achieving coupling of macroscopic and microscopic physical processes at key locations.

The present invention relates to a method for determining a volume average Eshelby tensor of an inclusion of arbitrary shape in a particle reinforced composite material. The method comprises the following steps: step 1, establishing a two-phase microscopic equivalent geometric model of a particle reinforced composite material: the microscopic equivalent geometric model comprises a cubic matrix phase and particles of arbitrary shape as two phases of an inclusion phase, wherein the inclusion phase is located at the exact center of the cubic phase; step 2, establishing a quantitative correlation mechanism between a volume average Eshelby tensor and a volume average stress and strain of each phase: in an existing microscopic equivalent geometric model, the volume average Eshelby tensor is derived according to the Eshelby equivalent inclusion theory and the Mori-Tanaka inclusion random distribution hypothesis; step 3, obtaining a volume average Eshelby tensor by reverse analysis: using a finite element numerical method to calculate the volume average stress and strain in the inclusion phase and the matrix phase in the two-phase microscopic equivalent geometric model of the particle reinforced composite material, and obtaining a volume average Eshelby tensor of an inclusion of arbitrary shape by reverse analysis.

This invention discloses a method for inverting pavement temperature field parameters and fusing data. Based on heat conduction theory, a partial differential equation for the pavement temperature field is established. An interpolation algorithm is used to characterize the initial conditions, boundary conditions, and measurement point temperatures of the pavement temperature field. The solution domain is normalized, and random sampling is used to generate sampling point coordinates within the pavement temperature solution domain and at its boundaries. These coordinates are used as input variables for a deep neural network. Based on the sampling point coordinates, a deep neural network and an automatic differentiation algorithm are combined to obtain normalized operator values for the sampling points. The measured temperature data is integrated with the initial and boundary conditions, and a total loss function for the deep neural network is constructed using a weighted summation method. The deep neural network is trained using gradient descent and the total loss function, and adaptive sampling is performed based on the partial differential equation loss of the current neural network, ultimately achieving pavement temperature field prediction. This invention achieves high-precision prediction of the pavement temperature field.

The invention relates to a method for identifying the mechanical property of each composition phase of a multiphase material, which comprises the following steps: firstly, pretreating the surface of a material to be detected, obtaining grain orientation and grain boundary distribution through EBSD, selecting an indentation position in a target phase single grain, and implementing a nanoindentation experiment to obtain a load-displacement curve; then, scanning the three-dimensional morphology of the indentation through AFM, and extracting the depth of a feature point; establishing a single crystal three-dimensional nanoindentation CPFEM model, endowing crystal orientation measured by EBSD, and simulating to obtain a curve and morphology depth; fitting an experiment curve and a simulation curve by using a parabolic function to obtain a characteristic coefficient, and incorporating the characteristic coefficient and the morphology depth into a back analysis objective function; and finally, carrying out back analysis by adopting a global optimization algorithm to solve crystal plasticity parameters, and outputting a single crystal constitutive parameter set. Compared with the prior art, through curve and morphology double-information constraint and three-dimensional simulation, the deviation of a traditional method is overcome, the parameter identification precision and reliability are improved, and the method is suitable for multi-phase materials such as high-strength steel and titanium alloy.