185 results about "Conduction equation" patented technology

The invention relates to an error compensation method of a birefringence self-calibration laser level meter, in particular to the field of laser level meters, and aims to improve the precision of the laser level meter by combining a birefringence effect, physical modeling and neural network optimization. Firstly, temperature data are collected in real time, Kalman filtering is used for noise reduction, and accurate data are provided for physical modeling; then, through physical constraints such as a heat conduction equation and a Jones matrix, a coupling relation between the temperature gradient and optical parameter changes is established; then, dynamically optimizing the refractive index correction by using a physical information neural network to avoid an overfitting problem; and finally, calculating optical path difference compensation by using a hardware accelerator, correcting a system error in real time, and feeding back and adjusting a network weight. According to the method, the precision and the stability of the laser level meter in an environment with relatively large temperature change are effectively improved.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a transformer overheating fault intelligent diagnosis system based on a physical information neural network. According to the invention, physical constraint filtering is carried out on signals through the adaptive noise suppression module; a loss function fusing a heat conduction equation, a gas decomposition kinetic equation and an insulation aging kinetic equation is constructed through a physical information neural network, and coupling modeling of temperature and gas and collaborative prediction of the aging state of insulation paper are achieved; spatial topological features and time sequence features are extracted through a multi-modal feature fusion module, and cross-modal association is established by adopting an attention mechanism; predicting a future feature trajectory through a fault evolution prediction module and outputting hierarchical early warning; and finally, outputting fault types, severity and maintenance suggestions. According to the method, a physical mechanism and data intelligence are deeply fused, advanced early warning and accurate positioning of an overheat fault are realized, and meanwhile, the blank that insulation failure cannot be pre-judged in the prior art is filled.

The invention relates to the technical field of tunnel engineering safety, in particular to a tunnel fire multi-stage damage collaborative prediction method and system, and the method comprises the steps: constructing a data simulation fusion model, and carrying out the processing of fire and tunnel structure parameter data, and obtaining a multi-working-condition parameter database; constructing a heat conduction equation, a fire plume and wall surface heat exchange relational expression, a boundary layer correction model and a comprehensive damage evaluation model, and analyzing the equation, the relational expression and the model by utilizing a multi-physical field coupling unified boundary condition to obtain a multi-physical boundary constraint condition; obtaining a multi-physical constraint loss function based on a network architecture and a multi-physical boundary constraint condition, and further obtaining a comprehensive constraint loss function of a temperature field-stress field-damage index; constructing a PINN-LSTM network architecture and a damage evolution analysis model based on the fire ending initial state coding vector, the fire course feature vector and the cooling process feature vector; and performing linkage analysis on the function, the frame and the model to predict and monitor the transient damage and the long-term creep damage of the tunnel.

The invention relates to the technical field of flexible circuit board manufacturing and packaging, in particular to an FPC assembly injection molding packaging structure and method based on dynamic mold flow control, and the structure comprises an FPC assembly, a first injection molding layer wrapping a welding spot area of the FPC assembly, and a second injection molding layer wrapping the first injection molding layer and the FPC assembly. The second injection molding layer is provided with an anchoring column penetrating through the reserved channel of the first injection molding layer or the through hole of the FPC assembly, and the anchoring column and the FPC assembly or the first injection molding layer form a mechanical interlocking structure. According to the FPC assembly injection molding packaging structure and method based on dynamic mold flow control, the electronic equipment and the storage medium, through a sandwich structure and in-situ mechanical interlocking design, the process control of a non-Newtonian fluid shear model and an unsteady state heat conduction equation is combined; the technical problems that in the prior art, procedures are tedious, stress concentration is caused by CTE mismatching, and welding spots are prone to being damaged in the injection molding process are solved.

The invention belongs to the field of laser processing and numerical simulation, and particularly relates to a finite element modeling and analysis method for a nanosecond pulse laser target material. The method comprises the following steps: establishing and loading a laser heat source model; establishing a target material finite element model and carrying out grid division; establishing and solving a transient heat conduction equation; carrying out multi-cycle iterative solution and post-processing; and performing model verification and parameter analysis. According to the method, the laser heat source model is established, the adaptive grid encryption strategy for temperature gradient optimization is adopted, and the transient solution algorithm is combined, so that compared with a traditional simplified analysis model or general commercial software simulation, the prediction precision of the target material temperature field spatio-temporal evolution law under the nanosecond pulse laser effect is remarkably improved. The method can accurately predict the temperature distribution and evolution law of the target material under the action of laser, has the advantages of high modeling precision, good calculation efficiency, wide application range and the like, and is suitable for engineering applications such as laser processing and damage evaluation of optical materials and composite materials.

The invention discloses a grounding grid electric heating power multi-field coupling modeling method and system considering soil nonlinear breakdown, and belongs to the technical field of power system grounding grids. The method comprises the following steps: establishing a three-dimensional geometric model containing a soil domain and a grounding grid conductor; defining non-linear conductivity characteristics of the soil; setting multi-physical field parameters and corresponding boundary conditions of the three-dimensional geometric model; and establishing a multi-physical field coupling control equation set including an electric field equation, a heat conduction equation and a thermal stress equation, and solving by adopting a finite element method to obtain three-dimensional space distribution data of the grounding grid under lightning current impact. According to the invention, on the basis of fully considering the nonlinear breakdown characteristic of the soil, the accurate simulation of the electric heating power multi-physical field behavior of the grounding grid under the impact current effect is realized, and the accuracy of impact impedance, potential distribution and temperature rise prediction is obviously improved.

The invention discloses a power consumption prediction and optimization method in chip design, and relates to the technical field of chip design and energy efficiency optimizing.The method comprises the steps that a circuit netlist is analyzed, functional blocks are divided, and an association diagram is constructed; generating a typical working load containing a transient peak value and a steady-state interval based on actual application; calculating dynamic and static power consumption, and considering temperature sensitive leakage current; constructing a three-dimensional thermal model, gridding a chip, solving a heat conduction equation, and outputting temperature field distribution; three-level optimization of clock gating, DVFS and data flow reconstruction is carried out on the overtemperature area; the optimized parameters are imported into a simulation tool to verify the effect, and robustness is confirmed through Monte Carlo simulation. According to the method, the power consumption prediction precision and optimization pertinence are improved, the temperature distribution uniformity is improved, the power consumption and performance are balanced, the number of design iterations is reduced, and the chip reliability and energy efficiency ratio are enhanced.

The invention relates to the technical field of metal composite materials, in particular to a metal composite material production process dynamic simulation method based on digital twinning. Comprising the following steps: constructing a digital twin model comprising a physical entity layer, a virtual model layer and a connection layer, and establishing a Fourier neural operator model embedded with a Navier Stokes equation and a heat conduction equation constraint; real-time molten pool monitoring data are mapped into model input through a connecting layer, and advanced time step deduction is executed by using a deep learning model to predict the state of a molten pool; based on the differentiable characteristic of a physical information neural operator, calculating the gradient of a prediction state and an ideal target by using an automatic differential algorithm, generating a process parameter field through reverse iteration updating, and discretizing the process parameter field into a galvanometer control instruction; and when the risk of aggregation of the reinforced phase particles is predicted to exist, automatically generating a swing scanning strategy to realize active suppression. The method gives consideration to simulation precision and real-time performance.

The invention discloses a thermal management control method and device of a solid-state battery, a vehicle and a computer readable storage medium. The solid-state battery is internally provided with a phase change material; the method comprises the following steps: monitoring the state change of the phase change material in real time; predicting thermal load distribution of the solid-state battery by adopting a dynamic thermal load estimation algorithm based on the state change of the phase change material, and generating a prediction result; according to the dynamic thermal load estimation algorithm, thermal load distribution in the solid-state battery is calculated in real time by establishing a coupling relationship between a phase change material state change parameter and a heat conduction equation; and generating a self-adaptive control strategy based on the prediction result of the thermal load distribution so as to adjust the operation parameters of the thermal management system. By applying the technical scheme of the invention, the problems that the thermal management system cannot accurately sense the internal thermal state of the battery, response lags behind, the prediction capability is lacked and full life cycle optimization cannot be realized can be solved.

The invention discloses a fidelity simulation method and system for a mine catastrophe scene, and relates to catastrophe simulation. The method comprises the steps of obtaining mine disaster historical data; performing statistical analysis and feature extraction on the historical data by adopting a multi-dimensional correlation analysis algorithm to obtain a main control element type set of the mine disaster and a weight coefficient of each main control element; setting an underground catastrophe scene reproduction scheme of each main control element type according to the main control element type set; catastrophe process monitoring data are collected in the target simulation area; establishing a mapping relation model between the main control elements and the disaster characteristic parameters through a machine learning algorithm; and generating an arrangement scheme of the underground catastrophe simulation device according to the mapping relation model. For the problem that mine catastrophe simulation lacks physical mechanism constraints in the prior art, residual errors of a gas diffusion equation, a heat conduction equation and a fluid dynamic equation are introduced into neural network training to serve as physical constraint loss items, and the generalization ability of simulation under different geological conditions and mining modes is improved.

The invention relates to the technical field of environment monitoring, in particular to a building decoration environment harmful gas dynamic monitoring method based on deep learning, which comprises the following steps: acquiring temperature, humidity, volatile organic compound concentration, carbon dioxide concentration, energy consumption and equipment attitude in a building model coordinate system, and eliminating redundant channels according to spatial topology to form a simplified data stream; dense features are extracted from the simplified data flow through a space-time auto-encoder, query key values are generated through quantification, and adjacent historical features are retrieved and spliced into a fusion feature vector; inputting the fused feature vector and a sensing node coordinate into a physical neural network of an embedded gas diffusion and heat conduction equation, and predicting a temperature gradient and regional carbon equivalent emission; calculating a hazard index field according to prediction, heat flow simulation, construction progress and a material release rate, iteratively optimizing a sensing node set and writing the sensing node set into an environment mirror image body; and reconstructing a coupling field in the environment mirror image body, comparing a measured value to obtain a residual field, and updating a hazard index field and a sensing node set when the environment mirror image body is abnormal.

The invention relates to the technical field of detector testing, and discloses a multi-parameter testing system and method for thermal characteristics of a refrigeration type infrared detector, and the system comprises a cooperative measurement module, a coupling analysis module, an optimization testing module, and a data analysis platform. The method corresponds to the system. According to the application, the temperature field, stress distribution and local heat flow data of the to-be-tested detector can be synchronously acquired, and the sensor is calibrated in a low-temperature vacuum environment, so that data drift in an extreme environment is avoided, and the accuracy of actually measured data is ensured; a coupling simulation model is built based on a heat conduction equation, a reduced order model and a Maxwell model, parameters are corrected by means of measured data, and thermal load, thermal mismatch stress and refrigeration efficiency evaluation results are accurately output; the cold screen coating performance and the cold finger thermophysical property of the detector can be tested, and the special test blank of key components is filled up; and multi-source data is integrated to identify anomalies, a three-dimensional thermal field interface is output, the optimization design is assisted, and the test comprehensiveness and accuracy are integrally improved.

The invention provides a soil moisture content calculation method based on an optical fiber temperature measurement technology, which comprises the following steps: acquiring a dry soil heat conductivity coefficient, dry soil density and porosity of a target area and a heat conductivity coefficient and density of water in the target area as soil basic parameters; based on an active heating method, obtaining temperature measurement values of the target area under different radial distances after the target area is heated to a steady state; the soil body basic parameters and the temperature measurement value are substituted into a soil body moisture content formula, and the soil body moisture content of the target area is obtained; wherein the soil mass moisture content formula is pre-constructed based on a soil mass steady-state heat conduction equation and the relationship between the heat conduction coefficient and the soil mass basic parameters, and represents the relationship among the heat conduction coefficient of the soil mass, the temperature and the soil mass moisture content. According to the method, the soil moisture content formula representing the relation among the soil basic parameters, the temperature measurement value and the soil moisture content is constructed, and tedious laboratory operation needed by an existing active heating method is simplified.

The invention discloses a seepage monitoring method and system based on an optical fiber sensor, and relates to the technical field of slope seepage monitoring, and the method comprises the steps: distributing distributed optical fiber sensors along an inclinometer pipe in a slope; laying an optical fiber heating system; a distributed temperature sensor DTS is used for collecting scattered light signals of the distributed optical fiber sensor; the scattered light signals collected by the DTS are demodulated; acquiring strain data in the slope; performing temperature compensation on the obtained displacement data; according to the obtained distributed temperature data and the displacement data after temperature compensation, the position and range of seepage in the slope are determined; calculating the seepage rate and the seepage flow of the corresponding position through the seepage model and the heat conduction equation; and judging the seepage degree of the side slope. According to the invention, aiming at the low precision of slope seepage monitoring in the prior art, the distributed temperature sensor DTS is utilized to collect the temperature distribution data of the optical fiber along the way, and temperature compensation and the RBF neural network model are combined, so that the precision of judging the slope seepage is improved.

The invention belongs to the technical field of geological energy storage, and particularly provides an underground chamber surrounding rock thermal-mechanical coupling fatigue phase field simulation method and system, and the method comprises the steps: building a phase field evolution equation through a phase field fracture model and a fatigue degradation function; on the basis of the calculation model, according to the air temperature and pressure in the cavern, the Newton heat exchange law is adopted to calculate cavern wall heat exchange, and a cavern wall heat conduction equation is constructed; on the basis of the calculation model, utilizing rock mass displacement and surrounding rock strain to construct a rock mass deformation equation; performing numerical discretization on the phase field evolution equation, the cave wall heat conduction equation and the rock mass deformation equation on a finite element grid unit, and performing thermal-mechanical coupling solution on all discretized equations through an iterative method to obtain evolution results of a temperature field, a stress field, a displacement field and a crack phase field of the underground chamber surrounding rock target area. According to the method, the phase field method is applied to thermal-mechanical coupling simulation of the underground gas storage chamber surrounding rock crack propagation condition, and the authenticity of chamber crack simulation is reflected to the maximum extent.

The invention relates to the technical field of laser welding, and provides a pressure vessel barrel laser welding all-position dynamic molten pool monitoring method which comprises the following steps: arranging a laser heat source and monitoring equipment to obtain molten pool temperature data and molten pool form data of a to-be-welded pressure vessel barrel; constructing a thermodynamic constraint based on a heat conduction equation, and training a molten pool monitoring model in combination with temperature data; constructing a hydrodynamic constraint based on a hydrodynamic equation, and fusing morphological data to further optimize the model; a target molten pool monitoring model with physical mechanism consistency is obtained by constructing thermal-fluid coupling physical constraints and combining with strengthening model training; and finally, inputting space-time coordinates of a to-be-measured position to realize inversion of the dynamic state of the molten pool in the all-position welding process. According to the method, multi-physics field constraint and data driving modeling are fused, the generalization ability and robustness of the model under the complex welding posture are improved, and the technical problem that the molten pool state is difficult to accurately monitor in all-position laser welding is effectively solved.

The invention discloses a subchannel division thought-based thermal hydraulic calculation method for a direct-current heat exchanger, and belongs to the technical field of fluid dynamic simulation and analysis of heat exchangers. The flowing area of the once-through heat exchanger is divided into a shell side area and a pipe side area according to different fluid characteristics of the primary side and the secondary side of the once-through heat exchanger. Dividing the shell side flow area into a plurality of adjacent sub-channels by taking the adjacent pipe walls as boundaries; the method is based on specific basic geometric parameters of a shell side sub-channel, including a sub-channel circulation area, an equivalent diameter, a wet perimeter, a heating perimeter and a gap width; establishing a heat exchanger tube side single-channel flow heat exchange basic equation; establishing a flow heat exchange basic equation in the heat exchanger shell side sub-channel; establishing a pipe wall heat conduction equation; and setting boundary conditions, and performing coupling calculation to obtain thermal parameters in sub-channels on the pipe side and the shell side of the heat exchanger. The method is used for solving the problems that one-dimensional calculation is inaccurate, and three-dimensional calculation is long in consumed time and large in calculation amount.

The invention provides an electrical equipment overheating hidden danger early warning method and system based on unmanned aerial vehicle multi-spectral imaging, and belongs to the technical field of power equipment state monitoring, and the method comprises the steps: firstly obtaining ultraviolet photons and spatial point cloud data collected by an unmanned aerial vehicle; a three-dimensional model is constructed based on the point cloud, and electric field distribution information is obtained through finite element analysis. And the photon data and the electric field information are combined, and the discharge charge quantity and distribution are obtained through space inversion correction. And calculating the discharge current density by using an energy dissipation model, and determining the discharge thermal power loss density in combination with the local electric field. And finally, a steady-state heat conduction equation is solved based on the heat conduction and dissipation parameters, temperature field distribution under heat balance is calculated, and early warning information is generated when the steady-state temperature exceeds a heat-resistant threshold value. According to the invention, early-stage accurate prediction and positioning of the hidden overheating fault of the electrical equipment caused by insulation degradation are realized.

The invention provides a laser cladding process parameter determination method based on finite element analogue simulation, and relates to the technical field of surface treatment. Comprising the following steps: importing a substrate material and a cladding layer material into finite element three-dimensional software to construct a corresponding finite element model; setting laser power, a preset temperature and a scanning path of the finite element model to obtain a finite element model of a variable process parameter set; performing finite element simulation by utilizing the final finite element model, and acquiring stress-strain data corresponding to each process parameter by utilizing a nonlinear heat conduction equation and an elastic-plastic stress-strain equation; and determining an optimal process parameter combination according to the stress-strain data. The method solves the problems that in the prior art, laser cladding Ni-60% WC composite powder lacks a systematic and accurate process parameter determination method when applied to the 45 steel surface, so that cracks, air holes and other defects are prone to being generated in a coating, and the comprehensive performance is difficult to stably improve.

The invention discloses a multi-objective optimization method and system based on building full life cycle energy consumption prediction, and belongs to the technical field of building energy saving and intelligent construction. Comprising the steps of constructing a physical-data fused building digital twin model, executing multi-time scale energy consumption prediction, solving a multi-objective optimization problem and recommending a dynamic optimal strategy. A physical information neural network is adopted to embed the building heat conduction equation into a neural network loss function, and deep fusion modeling of physical constraint and monitoring data is achieved. And a layered prediction architecture is designed, and different prediction models are adopted for a short term, a middle term and a long term and fusion output is carried out. And solving three-objective optimization of energy consumption, comfort and cost by adopting a non-dominated sorting genetic algorithm to obtain a Pareto optimal solution set. And screening an optimal scheme from the solution set for recommendation in combination with the situation information and the user preference. According to the method, the energy consumption prediction precision and the physical interpretability are effectively improved, and multi-target collaborative optimization and personalized strategy recommendation are 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 a liquid cooling energy storage system thermal management optimization method based on thermal diffusion modeling. The method is used for solving the problems that thermal runaway risk assessment of a liquid cooling energy storage system is inaccurate and energy consumption and cost are difficult to balance. The method comprises the following steps: firstly, collecting battery temperature, spacing, charging and discharging current, SOC, SOH, environment temperature and cooling liquid flow velocity data, dynamically adjusting sampling frequency based on a temperature change rate, and obtaining a fusion vector through filtering fusion denoising; inputting the three-dimensional unsteady-state heat conduction model into COMSOL to construct a multi-physical-field coupling model, and obtaining an initial heat diffusion probability through a three-dimensional unsteady-state heat conduction equation; then optimizing the probability by using an adaptive neural fuzzy inference system; and finally, constructing a multi-objective function by taking the optimized probability as a constraint, and outputting an optimal cooling liquid flow rate and an optimal battery spacing parameter through iteration of an iDBO algorithm, so that the system safety, the energy consumption efficiency and the economical efficiency are improved.

The invention discloses an active infrared thermal imaging thermal diffusion parameter inversion method and system based on a physical information neural network, and belongs to the technical field of infrared thermal imaging nondestructive testing and thermophysical parameter identification. In order to solve the problems that an active infrared thermal imaging method is difficult to steadily invert spatial distribution thermal diffusion parameters under the condition of only single-side surface temperature measurement and is sensitive to measurement noise, the method comprises the following steps: collecting surface space-time temperature field data of a tested piece under thermal excitation, and calculating a relative temperature field; normalizing the space-time coordinates, and constructing a multi-output physical information neural network; the equivalent surface heat conduction equation and the boundary and initial conditions thereof serve as a loss function of a physical constraint embedded neural network, and a Huber loss function is adopted to calculate a data fitting item; a neural network is optimized through joint training, a global volume thermal diffusion coefficient, a global equivalent thermal loss coefficient, a relative thermal diffusion coefficient field and a relative thermal loss coefficient field of spatial distribution are synchronously inverted, and a high signal-to-noise ratio temperature field is reconstructed. The method is used for material surface nondestructive testing.

The invention relates to the technical field of interface thermal resistance calculation, and discloses a method for measuring and calculating interface thermal resistance based on an infrared imaging technology, which comprises the following steps: fixing and aligning paired upper and lower test pieces to form a to-be-measured contact interface, respectively preheating to a preset initial temperature difference and stabilizing, and monitoring and recording temperature change and test piece thermophysical parameters; enabling the test piece to be in contact, starting infrared imaging equipment to record full-field transient temperature data in a temperature equalization process, and forming a three-dimensional data matrix; building a thermal resistance correlation model, constructing a heat conduction equation in combination with the parameters to solve a simulated temperature field, and inverting related heat conduction coefficients by using a conjugate gradient method; and calculating microscopic and total contact thermal resistance according to the inversion coefficient and the geometric parameters, and deducing macroscopic thermal resistance. According to the method, non-intrusive transient infrared temperature measurement is combined with a reverse heat transfer algorithm, so that the microscopic thermal resistance, the macroscopic thermal resistance and the total contact thermal resistance are accurately distinguished and quantified.

The invention provides an unconventional oil and gas reservoir heat-fluid-solid coupling numerical simulation method and system. The method comprises the steps that a multiphase numerical model of a coupling temperature field, a seepage field and a stress field is built; the multiphase numerical model is integrated with a Cahn-Hilliard equation, a heat conduction equation, a continuity equation, a Navier-Stokes equation and a mechanical equilibrium equation; determining a model computational domain of the multiphase numerical model; performing grid discretization processing on the model calculation domain and performing grid refinement processing on the peripheries of the mass flow inlet and the pressure outlet to obtain a plurality of grid units; inputting the environmental parameters and the initial condition parameters into the multiphase numerical model, controlling the multiphase numerical model to perform discrete calculation in each grid unit, judging whether a convergence condition is met or not, and if yes, updating the physical property parameters of the multiphase fluid according to the current temperature and pressure, and outputting a numerical simulation result of the unconventional oil and gas reservoir. According to the invention, the productivity prediction deviation can be reduced.

This invention provides an intelligent diagnostic method for building facade defects based on multimodal fusion using infrared thermal imaging, belonging to the field of building inspection technology. The method includes: simultaneously acquiring infrared thermal images, visible light images, and 3D point cloud data to construct a multimodal dataset; segmenting hot spot regions using an improved morphological watershed algorithm and extracting contour and temperature features; identifying surface cracks and spalling areas using a bi-branch attention network to generate texture defect feature maps; calculating curvature distribution and thermal deformation gradient through spatial registration constrained by the heat conduction equation; fusing multi-source features to calculate the hot spot morphological dispersion degree (TSMD) and structural risk quantification factor (SRQF); constructing a defect risk decision matrix to output defect type, location, and risk level; and overlaying the diagnostic results onto a BIM model to generate a 3D visualization report and predict thermodynamic evolution trends. This invention achieves collaborative analysis of multimodal data, accurately quantifies defect risks, and solves the problems of poor anti-interference, inaccurate segmentation, and large registration errors in traditional methods.

The invention provides a thermal response-seismic wave fused pipeline leakage point detection method, device and equipment, and relates to the technical field of underground pipeline leakage detection. The method comprises the following steps: acquiring seismic wave signals and time-space thermal response data obtained by detecting an underground pipeline; inputting the space-time thermal response data into a space-time convolutional neural network for space-time feature extraction to obtain a thermal field change mode of the underground pipeline; inputting the thermal field change mode into a physical information neural network for inversion to obtain first leakage source information of the underground pipeline; wherein the physical information neural network takes a heat conduction equation as a hard constraint; performing inversion on the seismic wave signal to obtain second leakage source information of the underground pipeline; and determining a leakage point detection result of the underground pipeline based on the first leakage source information and the second leakage source information. According to the invention, omnibearing accurate sensing of the deep buried leakage point from the spatial position to the leakage state can be realized, and the detection depth and the positioning precision are improved.

The application discloses a concentration gradient design method of a laser amplifier gain medium and the laser amplifier gain medium, and relates to the technical field of laser amplification, and aims to solve the heat effect problem that heat distribution is uneven due to uneven pump light absorption distribution of the laser amplifier gain medium. Technical points of the application include: according to the heat conduction equation, the phase difference of each section of the crystal corresponding to the seed light passing through the pump light region when the laser amplifier amplifies the seed light is calculated and obtained; according to the phase difference of each section of the crystal through which the seed light passes being equal, the phase difference of each section of the crystal corresponding to the seed light passing through the pump light region is set to be equal; the absorption coefficient of each section of the crystal is obtained by iterative solution using simulation software; and the concentration gradient of each section of the crystal is calculated and obtained according to the relationship between the absorption coefficient and the concentration gradient. According to the application, the concentration distribution of the laser amplifier crystal is designed according to the depolarization generated by the seed light passing through the amplification laser medium, so that the purpose of reducing the thermal depolarization effect from the root is achieved.

The application relates to the technical field of polymer material processing and molding, and discloses a temperature gradient control method for melting and plasticizing of food packaging PET bottle blanks. The method aims to solve the problems of static temperature control, poor melt homogeneity and weak process adaptability in the traditional plasticizing process. The method comprises the following steps: constructing an axial partition temperature setting model, dividing a solid conveying section, a melting transition section and a melt homogenization section and setting a reference temperature interval; deploying a distributed temperature sensing array to collect temperatures at key positions in real time; establishing a melt thermal state prediction model based on a non-Newtonian fluid heat conduction equation; dynamically regulating and controlling heating and cooling through a PID compound algorithm to realize closed-loop control of axial gradient and radial uniformity; and combining a process database to perform adaptive parameter correction. The application can significantly improve temperature control precision and melt homogeneity, enhance adaptability to raw material changes and high-speed production, effectively reduce bottle blank internal stress, wall thickness deviation and acetaldehyde content, and guarantee product quality and food safety.

The application relates to a multi-field coupling method for a spot welding process of a key part of rail transit, and the method establishes an electric-thermal field control equation, an electromagnetic field control equation and a heat flow field control equation for a resistance spot welding process, wherein the electric-thermal field control equation comprises a potential balance equation and a heat conduction equation. The application realizes the collaborative calculation and cross-model data transmission of key physical quantities such as current density, electromagnetic force, Joule heat and temperature distribution between different energy fields by constructing a multi-physical field coupling model of an electric field, an electromagnetic field and a temperature field, and improves the integrity and consistency of the simulation of the resistance spot welding process.