278 results about "Conduction equation" patented technology

The invention provides an infrared thermal imaging building facade defect intelligent diagnosis method based on multi-modal fusion, and relates to the technical field of building detection.The method comprises the steps that infrared thermal imaging, visible light images and three-dimensional point cloud data are synchronously collected to construct a multi-modal data set; segmenting a hot spot region by adopting an improved morphological watershed algorithm and extracting contour and temperature features; recognizing a surface crack and peeling area based on a double-branch attention network to generate a texture defect feature map; curvature distribution and thermal deformation gradient are calculated through space registration constrained by a heat conduction equation; multi-source features are fused to calculate a hot spot form dispersion TSMD and a structure risk quantification factor SRQF; constructing a defect risk decision matrix to output defect types, positions and risk levels; and superposing the diagnosis result to a BIM model to generate a three-dimensional visual report and predicting a thermodynamic evolution trend. The multi-modal data collaborative analysis is realized, the defect risk is accurately quantified, and the problems of poor anti-interference performance, inaccurate segmentation and large registration error of a traditional method are solved.

The invention discloses a geothermal field parameter inversion calculation method, device and system, and a storage medium. The method comprises the following steps: establishing a geophysical stratified model; through Monte Carlo sampling of preset parameter spaces of the crustal heat generation rate and the heat conductivity, a temperature value is calculated in combination with a heat conduction equation, and a Gaussian likelihood function evaluation model is constructed to predict the matching degree of the temperature and the actually measured temperature; obtaining the optimal estimation of the thermal parameters, a confidence interval and a correlation matrix among the parameters based on the posterior probability distribution; and according to the correlation matrix, taking a high-confidence result generated by Monte Carlo inversion as priori knowledge of a physical guidance neural network PINNs, and finally outputting a thermal parameter spatial distribution prediction result of the target area through parameter initialization constraint, output layer range limitation and a physical regularization loss item. By adopting the technical scheme of the invention, the defects that the existing actually measured geothermal field parameters are rare and the regional characteristics cannot be described and the geophysical joint inversion of the geothermal field parameters cannot be realized in the prior art are overcome.

The invention relates to the technical field of temperature measurement, in particular to a multi-zone temperature distribution real-time calibration method based on a heating body, which comprises the following steps of: 1, etching on the surface of a metal alloy heating body of which the resistance temperature coefficient is greater than a preset material threshold value to form N discrete series resistance heating units which are electrically connected in series but thermally discrete; 2, establishing a resistance-temperature dynamic relation library of each discrete series resistance heating unit; 3, synchronously measuring the real-time resistance value of each unit when the heating body works; 4, reversely deducing the temperature of a unit center point through a unit exclusive relational expression according to the real-time resistance value, and reconstructing a continuous temperature distribution matrix on the surface of the heating body in combination with a heat conduction equation; and 5, comparing the target temperature field with the real-time temperature field matrix, and adjusting the driving power of the corresponding unit in the out-of-tolerance region. Through continuous calibration and temperature adjustment, accurate control of a temperature field can be maintained in different use environments.

The invention discloses a power distribution network harmonic suppression and heat loss evaluation method and system, and relates to the technical field of electric energy quality optimization and heat loss evaluation, and the method comprises the steps: collecting a power distribution network signal, extracting harmonic features, and calculating the harmonic contribution degree of each load based on a harmonic power flow; cable additional heat loss caused by harmonic current is calculated, and cable temperature prediction is carried out based on a transient heat conduction equation; and dynamically adjusting parameters of the harmonic compensation device according to harmonic treatment and heat loss evaluation results, and optimizing load scheduling. According to the method, more accurate harmonic source identification and harmonic power flow calculation are provided, and the harmonic treatment accuracy is improved; in cable heat loss evaluation, eddy current loss modeling, heat conduction analysis and dynamic temperature prediction are introduced, so that the operation safety of the cable is enhanced; dynamic harmonic suppression optimization and load scheduling are combined, a closed-loop regulation mechanism is formed, the electric energy quality is improved, and meanwhile, the cable overheating risk is effectively avoided.

The invention relates to the technical field of chemical safety and intelligent control, in particular to an explosion-proof intelligent temperature control method and system for a hydrogen peroxide storage tank based on multi-modal monitoring, and the method comprises the steps: collecting multi-dimensional data such as temperature, pressure and H2O2 concentration through a sensor array, carrying out the Kalman filtering and wavelet transform denoising, recognizing local abnormal points through an improved WMDS-DBSCAN algorithm, and obtaining the explosion-proof intelligent temperature control of the hydrogen peroxide storage tank based on the WMDS-DBSCAN algorithm. Predicting a hot spot diffusion trend in combination with an unsteady heat conduction equation and an RF-ADI algorithm; weighted Delaunay triangulation is utilized to construct a self-adaptive monitoring grid, risk area probability distribution is output through an SAM-LSTM-CNN hybrid neural network, and a dynamic amplitude limiting fuzzy PID controller adjusts the opening degree of a nozzle to achieve temperature control. According to the method, multi-modal data and an intelligent algorithm are fused, abnormal accurate detection, risk prediction and self-adaptive temperature control are realized, a closed-loop optimization mechanism is formed, and the operation safety and reliability of the hydrogen peroxide storage tank are effectively improved.

The invention relates to a turbine blade global temperature field reconstruction method based on a multi-modal physical constraint network, and belongs to the technical field of aero-engine thermal management. Aiming at the problems of insufficient global heat conduction path modeling, lack of physical rules and blank region differentiation perception, carrying out normalization and position coding on sparse temperature measurement points to form a Transform encoder input sequence; extracting features through an encoder and compressing the features into global feature vectors through self-attention pooling; decoding the image into a temperature field image by adopting a U-Net generator fused with jump connection; a multi-scale discriminator is constructed, a semantic weighting mechanism is introduced, and differentiated weights are distributed to cooling holes, tenons and pressure surface areas; a physical constraint loss and local energy conservation loss are constructed based on a heat conduction equation, and a weighted training model is combined with confrontation loss and temperature error loss. The method is used for providing high-precision temperature distribution data support for turbine blade structure optimization design, cooling system efficiency evaluation and thermal fatigue prevention.

The invention discloses a geothermal abnormal point identification system based on remote sensing detection. The system comprises a data layer which collects thermal infrared remote sensing data, multispectral / hyperspectral remote sensing data, radar data, geological and topographic data, meteorological data and geophysical prospecting data; the processing layer is used for extracting key features, capturing dynamic changes of geothermal anomalies, distinguishing continuous geothermal anomalies and transient events, combining hyperspectral data and magnetotelluric sounding data, and constructing'earth surface-deep part 'associated features; the analysis layer is used for learning a diffusion rule of geothermal anomalies along a fault zone through a graph propagation model, taking a geothermal field heat conduction equation as a loss function constraint by utilizing a physical information neural network, jointly training a temperature field prediction model, constructing a deep three-dimensional geological structure based on gravity and geophysical prospecting data, and constructing a geologic structure model; constructing a geothermal anomaly detection model through the features provided by the processing layer to recognize geothermal anomaly points; and the output layer is used for generating a geothermal anomaly probability graph.

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 automobile material temperature simulation analysis, in particular to an automobile cabin temperature field simulation analysis method and system based on multi-physics field coupling. According to the method, high-precision and high-efficiency simulation is realized through thermal-solid-fluid-electric coupling modeling in combination with the genetic algorithm, the neural network and reinforcement learning AI dynamic optimization, and the problems that the multi-physical field coupling effect cannot be comprehensively reflected and the parameter optimization efficiency is low in the prior art are solved. Time sequence analysis and dynamic boundary condition adjustment are introduced, transient working condition simulation is supported, and temperature field changes in actual driving can be better predicted. Through simultaneous solution of the Maxwell equation and the heat conduction equation, the temperature rise risk of the electronic component is accurately predicted, and the method is suitable for heat management optimization of key components such as a battery pack and a motor controller of a new energy automobile. Cloud high-performance calculation and edge end lightweight model cooperation are adopted, efficient simulation and real-time early warning are achieved, and rapid analysis and design optimization of extreme working conditions are supported.

The invention discloses an on-orbit spacecraft temperature prediction method and device based on a physical information neural network. The method comprises the following steps: S1, constructing an object model and an orbit heat source model according to a spacecraft to be predicted; s2, solving a space external heat flow of the orbit heat source model, and converting the space external heat flow into a volume heat flow of the object model; s3, constructing a physical information neural network; wherein a three-dimensional transient heat conduction equation is embedded in the physical information neural network; s4, designing a total loss function according to the volume heat flow and the physical information neural network; and S5, training the physical information neural network according to the total loss function to obtain a temperature prediction result of the spacecraft to be predicted. According to the method, the situation that model grids need to be divided in traditional finite element simulation is avoided, the calculation efficiency is improved, the calculation time is shortened, the temperature result can be predicted in real time, and the generalization ability and accuracy of the model are improved.

The invention provides a battery pack temperature equalization control method. According to the method, multi-zone temperature and heat dissipation distribution data acquisition is carried out, a temperature distribution model is established in combination with K-means clustering and a heat conduction equation, heat dissipation parameters are optimized by using a least square method, differential temperature control instructions are generated by using a PID control algorithm, and Q-learning reinforcement learning is introduced to dynamically adjust control parameters. According to the method, accurate monitoring and intelligent regulation and control of the internal temperature of the battery pack are achieved, the problems that a traditional temperature control system is lagged in response and poor in equalization effect are effectively solved, the temperature equalization performance of the battery pack is remarkably improved through multi-level data analysis and a self-adaptive control strategy, the service life of the battery is prolonged, and the service life of the battery pack is prolonged. And reliable guarantee is provided for safe and efficient operation of the new energy automobile power battery.

The invention discloses a power plant fire intelligent linkage disposal system, which comprises a high-precision sensing layer, a time sequence prediction engine, a game decision system and an execution control system, and is characterized in that the high-precision sensing layer collects original data through a distributed sensor, and the original data is preprocessed into 12-dimensional feature vectors through edge computing nodes; the time sequence prediction engine takes the 12-dimensional feature vector as input, adopts a physical constraint Transform model, embeds a heat conduction equation regularization item, and outputs a fire evolution probability graph; the game decision-making system generates an optimal evacuation path through a multi-target reinforcement learning algorithm based on a fire evolution probability graph and a feature vector, and generates an equipment control instruction through a three-level response mechanism; and the execution control system drives an executor to execute a control instruction through a time-sensitive network, and feeds back an equipment state to the game decision-making system in real time. According to the invention, all links are mutually linked and dynamically adjusted, and efficient cooperation and accurate response of fire monitoring, early warning, decision making and disposal are realized.

The invention discloses a transformer noise suppression method, system, equipment and medium, and the method comprises the steps: collecting the winding temperature, iron core temperature, cooling system working condition, load current and other operation parameters of a transformer in real time, constructing a multi-physical field coupling model covering electromagnetic, thermal and mechanical characteristics, and providing basic data for noise analysis; based on a heat conduction equation and a vibration acoustics theory, a mapping relation between a heat dissipation state and a transformer noise source is established, and dynamic influences of heat dissipation on noise amplitude and frequency are quantified; through combination of finite element simulation and a thermal network model, winding / iron core deformation caused by temperature change is analyzed, then a modulation rule of deformation on noise radiation characteristics is derived, and a heat dissipation state-physical deformation-noise characteristic transfer function is constructed; and based on the transfer function, dynamically adjusting operation parameters of the transformer by adopting a model predictive control and adaptive filtering technology, and minimizing noise output on the premise of ensuring heat dissipation efficiency.

The invention relates to an economic evaluation method and system for in-situ conversion of medium and low-cooked shale, and belongs to the technical field of shale oil development. Comprising the following steps: 1) establishing a medium-low mature shale in-situ conversion geological model; 2) constructing a three-dimensional heat conduction equation, setting a definite solution condition, and solving the three-dimensional heat conduction equation in combination with the thermophysical parameters to obtain a temperature field on each time-space node in the medium-low mature shale in-situ conversion geological model; the method comprises the steps of (1) obtaining a dynamic hydrocarbon generation process, (2) obtaining a hydrocarbon generation kinetic parameter, (3) obtaining a total energy output, (5) obtaining a total energy input in a heating process, and (6) calculating an energy consumption ratio (ER), and carrying out economic feasibility evaluation of a shale in-situ conversion technology. The method can calculate a dynamic hydrocarbon generation process at any time and position in a shale bed in real time, and obviously improves the prediction precision of the hydrocarbon generation amount.

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 PINN-based grinding temperature prediction method and a transfer learning model, and belongs to the field of slow feed grinding and the technical field of neural networks. The method comprises the following steps: establishing an unsteady state heat conduction control equation, and defining a composite boundary condition; calculating the heat flux density of a heat source based on set grinding process parameters and workpiece material characteristics; constructing a PINN temperature prediction model; based on sparse temperature measurement data, a gradient optimization algorithm is adopted to dynamically invert and correct a heat conduction coefficient and a convective heat transfer coefficient; establishing a transfer learning mechanism, and accelerating solution of a PINN temperature prediction model under a new working condition; high-risk regions exceeding the critical damage temperature of the material are identified based on the predicted temperature field, and processing parameters are optimized to prevent grinding burns. According to the method, the unsteady heat conduction equation is embedded into the neural network, empirical formula constraint is replaced, and the physical consistency of the dynamic process is ensured; meanwhile, the method can achieve the inversion of key physical parameters based on a very small number of temperature measurement points, and solves a problem of boundary condition uncertainty.

The invention discloses a concrete material quality detection method based on multi-parameter analysis, and relates to the technical field of concrete material quality detection.The method comprises the steps that concrete structure data are collected, and a plurality of original detection parameters representing concrete quality are obtained; performing preprocessing operation on the original detection parameters to remove abnormal values and unify dimensions, and obtaining a standardized target detection data set; constructing a weight distribution model, dynamically adjusting parameter weights in the weight distribution model according to current detection environment information, and outputting a dynamic weighted parameter set; performing training updating on historical detection data, performing fusion calculation on the dynamic weighting parameter set and a current detection result, and generating an optimized weight configuration parameter; and constructing a physical information neural network model, and embedding the mechanical equation and the heat conduction equation of the concrete material into a neural network loss function as constraint terms.

The invention discloses a workpiece core-surface zero-temperature-difference heating method, and belongs to the technical field of large workpiece heat treatment. The invention aims to solve the problem of overlarge temperature difference between the surface and the core in the heat treatment process of a large workpiece. Comprising the following steps: on the basis of a one-dimensional unsteady state heat conduction equation, obtaining a heat treatment furnace heating temperature field curve of a to-be-heated workpiece heated from an initial temperature to a set temperature in a heat treatment furnace with a set temperature by adopting a numerical simulation method; meanwhile, a self-resistance heating temperature field curve of the workpiece to be heated under the set current condition is obtained; heating a workpiece to be heated under the condition of a set linear heating rate of a heat treatment furnace and under the condition of a set current of self-resistance heating to obtain a comprehensive heating unsteady-state temperature field curve; and based on the comprehensive heating unsteady state temperature field curve, current is adjusted, self-resistance heating is conducted on the to-be-heated workpiece, the actual comprehensive heating temperature field curve of the to-be-heated workpiece tends to be stable, and uniform heating of the to-be-heated workpiece is achieved. The method is used for heat treatment of large castings and forgings.

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 decision control system and method based on temperature field and atmosphere analysis, and relates to the technical field of intelligent control. A monitoring module in the system obtains a temperature set and a gas concentration set; the trend analysis module constructs a three-dimensional model and establishes a coordinate system, a variation function is combined with a Kriging equation to supplement a temperature set to generate an expanded temperature set, the three-dimensional model is discretized into a plurality of nodes and is matched with points in the expanded temperature set through nearest neighbor search, a heat conduction equation and a convection boundary are set, and a finite element matrix equation set is constructed; solving to obtain a temperature field model and carrying out statistics to generate a temperature trend curve; a decision module compares the temperature trend curve, the gas concentration set and a process standard to obtain an abnormal section number, and analyzes a section temperature difference and a concentration error vector of the abnormal section number by adopting a fuzzy PID control algorithm to generate an adjustment vector; and the execution module performs automatic adjustment based on the adjustment vector, so that intelligent decision adjustment based on temperature field and atmosphere conjoint analysis is realized.

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 discloses a biological tissue internal temperature microwave chromatography method and system, and belongs to the technical field of microwave measurement. The problem that the internal temperature of the biological tissue cannot be accurately obtained by adopting a microwave radiation temperature measurement technology nowadays is solved. The method comprises the following steps: acquiring environmental thermal radiation rates under different environmental conditions, and acquiring temperature distribution data of a human tissue profile to be subjected to temperature measurement along with depth change under different environmental conditions by utilizing a real three-dimensional anatomical model, a heat conduction equation and a thermal radiation equation of the human tissue to be subjected to temperature measurement; calculating dielectric constants of the human tissue to be subjected to temperature measurement under different frequencies, and obtaining radiation brightness temperature data of different frequencies under different environmental conditions by combining the temperature distribution data and a real three-dimensional anatomical model of the human tissue to be subjected to temperature measurement; constructing a brightness temperature-temperature conversion matrix by adopting a least square method; and acquiring brightness temperature data of different frequencies of human tissue to be subjected to temperature measurement, substituting the brightness temperature data into the brightness temperature-temperature conversion matrix, and performing inversion to obtain temperatures of different depths of the human tissue to be subjected to temperature measurement. The method is suitable for temperature measurement.

The invention belongs to the technical field of soil humidity prediction methods, and particularly relates to a soil deep humidity prediction system and method based on near infrared spectrum and federated learning. The system comprises a near infrared spectrum acquisition device, an auxiliary information acquisition module, an edge end data preprocessing module, a federated learning client module, a cloud federated aggregation server and a man-machine interaction and equipment control module. The method comprises the following steps: establishing a surface humidity estimation model by collecting soil surface near-infrared reflectivity and environment auxiliary information; a deep humidity prediction model is constructed in combination with a heat conduction equation and machine learning, and the accuracy is improved by adopting weighted fusion. A federal learning framework is introduced, local training and cloud aggregation of each agricultural machine are realized, data privacy is protected, and the model generalization ability is improved. The system does not need to destroy the soil structure, has the advantages of non-contact, high efficiency, safety and expandability, and is suitable for intelligent prediction of large-range deep humidity in farmland and linkage control of agricultural operation.